id	sid	tid	token	lemma	pos
12235	1	1	Evaluating	evaluate	VBG
12235	1	2	the	the	DT
12235	1	3	Impact	Impact	NNP
12235	1	4	of	of	IN
12235	1	5	the	the	DT
12235	1	6	Long	Long	NNP
12235	1	7	-	-	HYPH
12235	1	8	S	S	NNP
12235	1	9	upon	upon	IN
12235	1	10	18th	18th	JJ
12235	1	11	-	-	HYPH
12235	1	12	Century	century	NN
12235	1	13	Encyclopedia	Encyclopedia	NNP
12235	1	14	Britannica	Britannica	NNP
12235	1	15	Automatic	Automatic	NNP
12235	1	16	Subject	Subject	NNP
12235	1	17	Metadata	Metadata	NNP
12235	1	18	Generation	generation	NN
12235	1	19	Results	result	VBZ
12235	1	20	ARTICLES	articles	NN
12235	1	21	Evaluating	evaluate	VBG
12235	1	22	the	the	DT
12235	1	23	Impact	Impact	NNP
12235	1	24	of	of	IN
12235	1	25	the	the	DT
12235	1	26	Long	Long	NNP
12235	1	27	-	-	HYPH
12235	1	28	S	S	NNP
12235	1	29	upon	upon	IN
12235	1	30	18th	18th	JJ
12235	1	31	-	-	HYPH
12235	1	32	Century	century	NN
12235	1	33	Encyclopedia	Encyclopedia	NNP
12235	1	34	Britannica	Britannica	NNP
12235	1	35	Automatic	Automatic	NNP
12235	1	36	Subject	Subject	NNP
12235	1	37	Metadata	Metadata	NNP
12235	1	38	Generation	generation	NN
12235	1	39	Results	result	VBZ
12235	1	40	Sam	Sam	NNP
12235	1	41	Grabus	Grabus	NNP
12235	1	42	INFORMATION	INFORMATION	NNP
12235	1	43	TECHNOLOGY	TECHNOLOGY	NNP
12235	1	44	AND	and	CC
12235	1	45	LIBRARIES	LIBRARIES	NNP
12235	1	46	|	|	NNP
12235	1	47	SEPTEMBER	SEPTEMBER	NNP
12235	1	48	2020	2020	CD
12235	1	49	https://doi.org/10.6017/ital.v39i3.12235	https://doi.org/10.6017/ital.v39i3.12235	NN
12235	1	50	Sam	Sam	NNP
12235	1	51	Grabus	Grabus	NNP
12235	1	52	(	(	-LRB-
12235	1	53	smg383@Drexel.edu	smg383@Drexel.edu	NNP
12235	1	54	)	)	-RRB-
12235	1	55	is	be	VBZ
12235	1	56	an	an	DT
12235	1	57	Information	Information	NNP
12235	1	58	Science	Science	NNP
12235	1	59	PhD	phd	NN
12235	1	60	Candidate	candidate	NN
12235	1	61	at	at	IN
12235	1	62	Drexel	Drexel	NNP
12235	1	63	University	University	NNP
12235	1	64	’s	’s	NNP
12235	1	65	College	College	NNP
12235	1	66	of	of	IN
12235	1	67	Computing	Computing	NNP
12235	1	68	and	and	CC
12235	1	69	Informatics	Informatics	NNP
12235	1	70	,	,	,
12235	1	71	and	and	CC
12235	1	72	Research	Research	NNP
12235	1	73	Assistant	Assistant	NNP
12235	1	74	at	at	IN
12235	1	75	Drexel	Drexel	NNP
12235	1	76	’s	’s	POS
12235	1	77	Metadata	Metadata	NNP
12235	1	78	Research	Research	NNP
12235	1	79	Center	Center	NNP
12235	1	80	.	.	.
12235	2	1	This	this	DT
12235	2	2	article	article	NN
12235	2	3	is	be	VBZ
12235	2	4	the	the	DT
12235	2	5	2020	2020	CD
12235	2	6	winner	winner	NN
12235	2	7	of	of	IN
12235	2	8	the	the	DT
12235	2	9	LITA	LITA	NNP
12235	2	10	/	/	SYM
12235	2	11	Ex	Ex	NNP
12235	2	12	Libris	Libris	NNP
12235	2	13	Student	Student	NNP
12235	2	14	Writing	Writing	NNP
12235	2	15	Award	Award	NNP
12235	2	16	.	.	.
12235	3	1	©	©	NNP
12235	3	2	2020	2020	CD
12235	3	3	.	.	.
12235	4	1	ABSTRACT	ABSTRACT	NNP
12235	4	2	This	this	DT
12235	4	3	research	research	NN
12235	4	4	compares	compare	VBZ
12235	4	5	automatic	automatic	JJ
12235	4	6	subject	subject	JJ
12235	4	7	metadata	metadata	NN
12235	4	8	generation	generation	NN
12235	4	9	when	when	WRB
12235	4	10	the	the	DT
12235	4	11	pre-1800s	pre-1800s	,
12235	4	12	Long	long	JJ
12235	4	13	-	-	HYPH
12235	4	14	S	S	NNP
12235	4	15	character	character	NN
12235	4	16	is	be	VBZ
12235	4	17	corrected	correct	VBN
12235	4	18	to	to	IN
12235	4	19	a	a	DT
12235	4	20	standard	standard	NN
12235	4	21	<	<	XX
12235	4	22	s	s	NNP
12235	4	23	>	>	XX
12235	4	24	.	.	.
12235	5	1	The	the	DT
12235	5	2	test	test	NN
12235	5	3	environment	environment	NN
12235	5	4	includes	include	VBZ
12235	5	5	entries	entry	NNS
12235	5	6	from	from	IN
12235	5	7	the	the	DT
12235	5	8	third	third	JJ
12235	5	9	edition	edition	NN
12235	5	10	of	of	IN
12235	5	11	the	the	DT
12235	5	12	Encyclopedia	Encyclopedia	NNP
12235	5	13	Britannica	Britannica	NNP
12235	5	14	,	,	,
12235	5	15	and	and	CC
12235	5	16	the	the	DT
12235	5	17	HIVE	HIVE	NNP
12235	5	18	automatic	automatic	JJ
12235	5	19	subject	subject	JJ
12235	5	20	indexing	indexing	NN
12235	5	21	tool	tool	NN
12235	5	22	.	.	.
12235	6	1	A	a	DT
12235	6	2	comparative	comparative	JJ
12235	6	3	study	study	NN
12235	6	4	of	of	IN
12235	6	5	metadata	metadata	NN
12235	6	6	generated	generate	VBN
12235	6	7	before	before	IN
12235	6	8	and	and	CC
12235	6	9	after	after	IN
12235	6	10	correction	correction	NN
12235	6	11	of	of	IN
12235	6	12	the	the	DT
12235	6	13	Long	Long	NNP
12235	6	14	-	-	HYPH
12235	6	15	S	S	NNP
12235	6	16	demonstrated	demonstrate	VBD
12235	6	17	an	an	DT
12235	6	18	average	average	NN
12235	6	19	of	of	IN
12235	6	20	26.51	26.51	CD
12235	6	21	percent	percent	NN
12235	6	22	potentially	potentially	RB
12235	6	23	relevant	relevant	JJ
12235	6	24	terms	term	NNS
12235	6	25	per	per	IN
12235	6	26	entry	entry	NN
12235	6	27	omitted	omit	VBN
12235	6	28	from	from	IN
12235	6	29	results	result	NNS
12235	6	30	if	if	IN
12235	6	31	the	the	DT
12235	6	32	Long	Long	NNP
12235	6	33	-	-	HYPH
12235	6	34	S	S	NNP
12235	6	35	is	be	VBZ
12235	6	36	not	not	RB
12235	6	37	corrected	correct	VBN
12235	6	38	.	.	.
12235	7	1	Results	result	NNS
12235	7	2	confirm	confirm	VBP
12235	7	3	that	that	IN
12235	7	4	correcting	correct	VBG
12235	7	5	the	the	DT
12235	7	6	Long	long	JJ
12235	7	7	-	-	HYPH
12235	7	8	S	S	NNP
12235	7	9	increases	increase	VBZ
12235	7	10	the	the	DT
12235	7	11	availability	availability	NN
12235	7	12	of	of	IN
12235	7	13	terms	term	NNS
12235	7	14	that	that	WDT
12235	7	15	can	can	MD
12235	7	16	be	be	VB
12235	7	17	used	use	VBN
12235	7	18	for	for	IN
12235	7	19	creating	create	VBG
12235	7	20	quality	quality	NN
12235	7	21	metadata	metadata	NN
12235	7	22	records	record	NNS
12235	7	23	.	.	.
12235	8	1	A	a	DT
12235	8	2	relationship	relationship	NN
12235	8	3	is	be	VBZ
12235	8	4	also	also	RB
12235	8	5	demonstrated	demonstrate	VBN
12235	8	6	between	between	IN
12235	8	7	shorter	short	JJR
12235	8	8	entries	entry	NNS
12235	8	9	and	and	CC
12235	8	10	an	an	DT
12235	8	11	increase	increase	NN
12235	8	12	in	in	IN
12235	8	13	omitted	omitted	JJ
12235	8	14	terms	term	NNS
12235	8	15	when	when	WRB
12235	8	16	the	the	DT
12235	8	17	Long	Long	NNP
12235	8	18	-	-	HYPH
12235	8	19	S	S	NNP
12235	8	20	is	be	VBZ
12235	8	21	not	not	RB
12235	8	22	corrected	correct	VBN
12235	8	23	.	.	.
12235	9	1	INTRODUCTION	introduction	VB
12235	9	2	The	the	DT
12235	9	3	creation	creation	NN
12235	9	4	of	of	IN
12235	9	5	subject	subject	JJ
12235	9	6	metadata	metadata	NN
12235	9	7	for	for	IN
12235	9	8	individual	individual	JJ
12235	9	9	documents	document	NNS
12235	9	10	is	be	VBZ
12235	9	11	long	long	RB
12235	9	12	known	know	VBN
12235	9	13	to	to	TO
12235	9	14	support	support	VB
12235	9	15	standardized	standardized	JJ
12235	9	16	resource	resource	NN
12235	9	17	discovery	discovery	NN
12235	9	18	and	and	CC
12235	9	19	analysis	analysis	NN
12235	9	20	by	by	IN
12235	9	21	identifying	identify	VBG
12235	9	22	and	and	CC
12235	9	23	connecting	connect	VBG
12235	9	24	resources	resource	NNS
12235	9	25	with	with	IN
12235	9	26	similar	similar	JJ
12235	9	27	aboutness	aboutness	NN
12235	9	28	.1	.1	.
12235	9	29	In	in	IN
12235	9	30	order	order	NN
12235	9	31	to	to	TO
12235	9	32	address	address	VB
12235	9	33	the	the	DT
12235	9	34	challenges	challenge	NNS
12235	9	35	of	of	IN
12235	9	36	scale	scale	NN
12235	9	37	,	,	,
12235	9	38	automatic	automatic	JJ
12235	9	39	or	or	CC
12235	9	40	semi	semi	JJ
12235	9	41	-	-	JJ
12235	9	42	automatic	automatic	JJ
12235	9	43	indexing	indexing	NN
12235	9	44	is	be	VBZ
12235	9	45	frequently	frequently	RB
12235	9	46	employed	employ	VBN
12235	9	47	for	for	IN
12235	9	48	the	the	DT
12235	9	49	generation	generation	NN
12235	9	50	of	of	IN
12235	9	51	subject	subject	JJ
12235	9	52	metadata	metadata	NN
12235	9	53	,	,	,
12235	9	54	particularly	particularly	RB
12235	9	55	for	for	IN
12235	9	56	academic	academic	JJ
12235	9	57	articles	article	NNS
12235	9	58	,	,	,
12235	9	59	where	where	WRB
12235	9	60	the	the	DT
12235	9	61	abstract	abstract	JJ
12235	9	62	and	and	CC
12235	9	63	title	title	NN
12235	9	64	can	can	MD
12235	9	65	be	be	VB
12235	9	66	used	use	VBN
12235	9	67	as	as	IN
12235	9	68	surrogates	surrogate	NNS
12235	9	69	in	in	IN
12235	9	70	place	place	NN
12235	9	71	of	of	IN
12235	9	72	indexing	index	VBG
12235	9	73	the	the	DT
12235	9	74	full	full	JJ
12235	9	75	text	text	NN
12235	9	76	.	.	.
12235	10	1	When	when	WRB
12235	10	2	automatically	automatically	RB
12235	10	3	generating	generate	VBG
12235	10	4	subject	subject	JJ
12235	10	5	metadata	metadata	NN
12235	10	6	for	for	IN
12235	10	7	historical	historical	JJ
12235	10	8	humanities	humanity	NNS
12235	10	9	full	full	JJ
12235	10	10	texts	text	NNS
12235	10	11	that	that	WDT
12235	10	12	do	do	VBP
12235	10	13	not	not	RB
12235	10	14	have	have	VB
12235	10	15	an	an	DT
12235	10	16	abstract	abstract	JJ
12235	10	17	,	,	,
12235	10	18	anachronistic	anachronistic	JJ
12235	10	19	typographical	typographical	JJ
12235	10	20	challenges	challenge	NNS
12235	10	21	may	may	MD
12235	10	22	arise	arise	VB
12235	10	23	.	.	.
12235	11	1	One	one	CD
12235	11	2	key	key	JJ
12235	11	3	challenge	challenge	NN
12235	11	4	is	be	VBZ
12235	11	5	that	that	IN
12235	11	6	presented	present	VBN
12235	11	7	by	by	IN
12235	11	8	the	the	DT
12235	11	9	historical	historical	JJ
12235	11	10	“	"	``
12235	11	11	Long	Long	NNP
12235	11	12	-	-	HYPH
12235	11	13	S	s	NN
12235	11	14	”	"	''
12235	11	15	<	<	XX
12235	11	16	ſ	ſ	NNP
12235	11	17	>	>	XX
12235	11	18	.	.	.
12235	12	1	In	in	IN
12235	12	2	order	order	NN
12235	12	3	to	to	TO
12235	12	4	account	account	VB
12235	12	5	for	for	IN
12235	12	6	these	these	DT
12235	12	7	idiosyncrasies	idiosyncrasy	NNS
12235	12	8	,	,	,
12235	12	9	there	there	EX
12235	12	10	is	be	VBZ
12235	12	11	a	a	DT
12235	12	12	need	need	NN
12235	12	13	to	to	TO
12235	12	14	understand	understand	VB
12235	12	15	the	the	DT
12235	12	16	impact	impact	NN
12235	12	17	that	that	WDT
12235	12	18	they	-PRON-	PRP
12235	12	19	have	have	VBP
12235	12	20	upon	upon	IN
12235	12	21	the	the	DT
12235	12	22	automatic	automatic	JJ
12235	12	23	subject	subject	JJ
12235	12	24	indexing	indexing	NN
12235	12	25	output	output	NN
12235	12	26	.	.	.
12235	13	1	Addressing	address	VBG
12235	13	2	this	this	DT
12235	13	3	challenge	challenge	NN
12235	13	4	will	will	MD
12235	13	5	help	help	VB
12235	13	6	librarians	librarian	NNS
12235	13	7	and	and	CC
12235	13	8	information	information	NN
12235	13	9	professionals	professional	NNS
12235	13	10	to	to	TO
12235	13	11	determine	determine	VB
12235	13	12	whether	whether	IN
12235	13	13	or	or	CC
12235	13	14	not	not	RB
12235	13	15	they	-PRON-	PRP
12235	13	16	will	will	MD
12235	13	17	need	need	VB
12235	13	18	to	to	TO
12235	13	19	correct	correct	VB
12235	13	20	the	the	DT
12235	13	21	Long	Long	NNP
12235	13	22	-	-	HYPH
12235	13	23	S	s	NN
12235	13	24	when	when	WRB
12235	13	25	automatically	automatically	RB
12235	13	26	generating	generate	VBG
12235	13	27	subject	subject	JJ
12235	13	28	metadata	metadata	NN
12235	13	29	for	for	IN
12235	13	30	full	full	JJ
12235	13	31	-	-	HYPH
12235	13	32	text	text	NN
12235	13	33	pre-1800s	pre-1800s	''
12235	13	34	documents	document	NNS
12235	13	35	.	.	.
12235	14	1	The	the	DT
12235	14	2	problem	problem	NN
12235	14	3	of	of	IN
12235	14	4	the	the	DT
12235	14	5	Long	Long	NNP
12235	14	6	-	-	HYPH
12235	14	7	S	S	NNP
12235	14	8	in	in	IN
12235	14	9	Optical	Optical	NNP
12235	14	10	Character	Character	NNP
12235	14	11	Recognition	Recognition	NNP
12235	14	12	(	(	-LRB-
12235	14	13	OCR	OCR	NNP
12235	14	14	)	)	-RRB-
12235	14	15	for	for	IN
12235	14	16	digital	digital	JJ
12235	14	17	manuscript	manuscript	NN
12235	14	18	images	image	NNS
12235	14	19	has	have	VBZ
12235	14	20	been	be	VBN
12235	14	21	discussed	discuss	VBN
12235	14	22	for	for	IN
12235	14	23	decades.2	decades.2	NNP
12235	14	24	Many	many	JJ
12235	14	25	scholars	scholar	NNS
12235	14	26	have	have	VBP
12235	14	27	researched	research	VBN
12235	14	28	methods	method	NNS
12235	14	29	for	for	IN
12235	14	30	correcting	correct	VBG
12235	14	31	the	the	DT
12235	14	32	Long-	Long-	NNP
12235	14	33	S	S	NNP
12235	14	34	through	through	IN
12235	14	35	the	the	DT
12235	14	36	use	use	NN
12235	14	37	of	of	IN
12235	14	38	rule	rule	NN
12235	14	39	-	-	HYPH
12235	14	40	based	base	VBN
12235	14	41	algorithms	algorithm	NNS
12235	14	42	or	or	CC
12235	14	43	dictionaries.3	dictionaries.3	NN
12235	14	44	While	while	IN
12235	14	45	the	the	DT
12235	14	46	problem	problem	NN
12235	14	47	of	of	IN
12235	14	48	the	the	DT
12235	14	49	Long	Long	NNP
12235	14	50	-	-	HYPH
12235	14	51	S	S	NNP
12235	14	52	is	be	VBZ
12235	14	53	well	well	RB
12235	14	54	-	-	HYPH
12235	14	55	known	know	VBN
12235	14	56	in	in	IN
12235	14	57	the	the	DT
12235	14	58	digital	digital	JJ
12235	14	59	humanities	humanity	NNS
12235	14	60	community	community	NN
12235	14	61	,	,	,
12235	14	62	automatic	automatic	JJ
12235	14	63	subject	subject	JJ
12235	14	64	metadata	metadata	NN
12235	14	65	generation	generation	NN
12235	14	66	for	for	IN
12235	14	67	a	a	DT
12235	14	68	large	large	JJ
12235	14	69	corpus	corpus	NN
12235	14	70	of	of	IN
12235	14	71	pre-1800s	pre-1800	NNS
12235	14	72	documents	document	NNS
12235	14	73	is	be	VBZ
12235	14	74	rare	rare	JJ
12235	14	75	,	,	,
12235	14	76	as	as	IN
12235	14	77	is	be	VBZ
12235	14	78	research	research	NN
12235	14	79	about	about	IN
12235	14	80	the	the	DT
12235	14	81	application	application	NN
12235	14	82	and	and	CC
12235	14	83	evaluation	evaluation	NN
12235	14	84	of	of	IN
12235	14	85	existing	exist	VBG
12235	14	86	automatic	automatic	JJ
12235	14	87	subject	subject	JJ
12235	14	88	metadata	metadata	NN
12235	14	89	generation	generation	NN
12235	14	90	tools	tool	NNS
12235	14	91	on	on	IN
12235	14	92	18th	18th	JJ
12235	14	93	-	-	HYPH
12235	14	94	century	century	NN
12235	14	95	documents	document	NNS
12235	14	96	in	in	IN
12235	14	97	real	real	JJ
12235	14	98	-	-	HYPH
12235	14	99	world	world	NN
12235	14	100	information	information	NN
12235	14	101	environments	environment	NNS
12235	14	102	.	.	.
12235	15	1	The	the	DT
12235	15	2	impact	impact	NN
12235	15	3	of	of	IN
12235	15	4	the	the	DT
12235	15	5	Long	Long	NNP
12235	15	6	-	-	HYPH
12235	15	7	S	S	NNP
12235	15	8	upon	upon	IN
12235	15	9	automatic	automatic	JJ
12235	15	10	subject	subject	JJ
12235	15	11	metadata	metadata	NN
12235	15	12	generation	generation	NN
12235	15	13	results	result	NNS
12235	15	14	for	for	IN
12235	15	15	pre-1800s	pre-1800	NNS
12235	15	16	texts	text	NNS
12235	15	17	has	have	VBZ
12235	15	18	not	not	RB
12235	15	19	been	be	VBN
12235	15	20	extensively	extensively	RB
12235	15	21	explored	explore	VBN
12235	15	22	.	.	.
12235	16	1	The	the	DT
12235	16	2	research	research	NN
12235	16	3	presented	present	VBN
12235	16	4	in	in	IN
12235	16	5	this	this	DT
12235	16	6	paper	paper	NN
12235	16	7	addresses	address	NNS
12235	16	8	this	this	DT
12235	16	9	need	need	NN
12235	16	10	.	.	.
12235	17	1	The	the	DT
12235	17	2	paper	paper	NN
12235	17	3	reports	report	NNS
12235	17	4	results	result	VBZ
12235	17	5	from	from	IN
12235	17	6	basic	basic	JJ
12235	17	7	statistical	statistical	JJ
12235	17	8	analysis	analysis	NN
12235	17	9	and	and	CC
12235	17	10	visualization	visualization	NN
12235	17	11	using	use	VBG
12235	17	12	the	the	DT
12235	17	13	Helping	Helping	NNP
12235	17	14	Interdisciplinary	Interdisciplinary	NNP
12235	17	15	Vocabulary	Vocabulary	NNP
12235	17	16	Engineering	Engineering	NNP
12235	17	17	(	(	-LRB-
12235	17	18	HIVE	HIVE	NNP
12235	17	19	)	)	-RRB-
12235	17	20	tool	tool	NN
12235	17	21	automatic	automatic	JJ
12235	17	22	mailto:smg383@Drexel.edu	mailto:smg383@Drexel.edu	NNS
12235	17	23	INFORMATION	INFORMATION	NNP
12235	17	24	TECHNOLOGY	TECHNOLOGY	NNP
12235	17	25	AND	and	CC
12235	17	26	LIBRARIES	library	NNS
12235	17	27	SEPTEMBER	SEPTEMBER	NNP
12235	17	28	2020	2020	CD
12235	17	29	EVALUATING	evaluate	VBG
12235	17	30	THE	the	DT
12235	17	31	IMPACT	impact	NN
12235	17	32	OF	of	IN
12235	17	33	THE	the	DT
12235	17	34	LONG	long	JJ
12235	17	35	-	-	HYPH
12235	17	36	S	s	NN
12235	17	37	|	|	NNP
12235	17	38	GRABUS	grabus	NN
12235	17	39	2	2	CD
12235	17	40	subject	subject	JJ
12235	17	41	indexing	indexing	NN
12235	17	42	results	result	NNS
12235	17	43	,	,	,
12235	17	44	before	before	RB
12235	17	45	and	and	CC
12235	17	46	after	after	IN
12235	17	47	the	the	DT
12235	17	48	correction	correction	NN
12235	17	49	of	of	IN
12235	17	50	the	the	DT
12235	17	51	historical	historical	JJ
12235	17	52	Long	Long	NNP
12235	17	53	-	-	HYPH
12235	17	54	S	S	NNP
12235	17	55	in	in	IN
12235	17	56	the	the	DT
12235	17	57	3rd	3rd	JJ
12235	17	58	edition	edition	NN
12235	17	59	of	of	IN
12235	17	60	the	the	DT
12235	17	61	Encyclopedia	Encyclopedia	NNP
12235	17	62	Britannica	Britannica	NNP
12235	17	63	.	.	.
12235	18	1	Background	background	NN
12235	18	2	work	work	NN
12235	18	3	was	be	VBD
12235	18	4	conducted	conduct	VBN
12235	18	5	over	over	IN
12235	18	6	the	the	DT
12235	18	7	Summer	Summer	NNP
12235	18	8	and	and	CC
12235	18	9	Fall	Fall	NNP
12235	18	10	of	of	IN
12235	18	11	2019	2019	CD
12235	18	12	,	,	,
12235	18	13	and	and	CC
12235	18	14	the	the	DT
12235	18	15	research	research	NN
12235	18	16	presented	present	VBN
12235	18	17	was	be	VBD
12235	18	18	conducted	conduct	VBN
12235	18	19	during	during	IN
12235	18	20	Winter	Winter	NNP
12235	18	21	2020	2020	CD
12235	18	22	.	.	.
12235	19	1	The	the	DT
12235	19	2	work	work	NN
12235	19	3	was	be	VBD
12235	19	4	motivated	motivate	VBN
12235	19	5	by	by	IN
12235	19	6	current	current	JJ
12235	19	7	work	work	NN
12235	19	8	on	on	IN
12235	19	9	the	the	DT
12235	19	10	“	"	``
12235	19	11	Developing	develop	VBG
12235	19	12	the	the	DT
12235	19	13	Data	Data	NNP
12235	19	14	Set	Set	NNP
12235	19	15	of	of	IN
12235	19	16	Nineteenth	Nineteenth	NNP
12235	19	17	-	-	HYPH
12235	19	18	Century	Century	NNP
12235	19	19	Knowledge	Knowledge	NNP
12235	19	20	”	"	''
12235	19	21	project	project	NN
12235	19	22	,	,	,
12235	19	23	a	a	DT
12235	19	24	National	National	NNP
12235	19	25	Endowment	Endowment	NNP
12235	19	26	for	for	IN
12235	19	27	the	the	DT
12235	19	28	Humanities	Humanities	NNPS
12235	19	29	collaborative	collaborative	JJ
12235	19	30	project	project	NN
12235	19	31	between	between	IN
12235	19	32	Temple	Temple	NNP
12235	19	33	University	University	NNP
12235	19	34	’s	’s	POS
12235	19	35	Digital	Digital	NNP
12235	19	36	Scholarship	Scholarship	NNP
12235	19	37	Center	Center	NNP
12235	19	38	and	and	CC
12235	19	39	Drexel	Drexel	NNP
12235	19	40	University	University	NNP
12235	19	41	’s	’s	POS
12235	19	42	Metadata	Metadata	NNP
12235	19	43	Research	Research	NNP
12235	19	44	Center	Center	NNP
12235	19	45	.	.	.
12235	20	1	The	the	DT
12235	20	2	grant	grant	NN
12235	20	3	is	be	VBZ
12235	20	4	part	part	NN
12235	20	5	of	of	IN
12235	20	6	a	a	DT
12235	20	7	larger	large	JJR
12235	20	8	project	project	NN
12235	20	9	,	,	,
12235	20	10	Temple	Temple	NNP
12235	20	11	University	University	NNP
12235	20	12	’s	’s	POS
12235	20	13	“	"	``
12235	20	14	19th	19th	JJ
12235	20	15	-	-	HYPH
12235	20	16	Century	Century	NNP
12235	20	17	Knowledge	Knowledge	NNP
12235	20	18	Project	Project	NNP
12235	20	19	,	,	,
12235	20	20	”	"	''
12235	20	21	which	which	WDT
12235	20	22	is	be	VBZ
12235	20	23	digitizing	digitize	VBG
12235	20	24	four	four	CD
12235	20	25	historical	historical	JJ
12235	20	26	editions	edition	NNS
12235	20	27	of	of	IN
12235	20	28	the	the	DT
12235	20	29	Encyclopedia	Encyclopedia	NNP
12235	20	30	Britannica.4	Britannica.4	NNP
12235	20	31	The	the	DT
12235	20	32	next	next	JJ
12235	20	33	section	section	NN
12235	20	34	of	of	IN
12235	20	35	this	this	DT
12235	20	36	paper	paper	NN
12235	20	37	presents	present	NNS
12235	20	38	background	background	NN
12235	20	39	covering	cover	VBG
12235	20	40	the	the	DT
12235	20	41	historical	historical	JJ
12235	20	42	Encyclopedia	Encyclopedia	NNP
12235	20	43	Britannica	Britannica	NNP
12235	20	44	data	datum	NNS
12235	20	45	,	,	,
12235	20	46	the	the	DT
12235	20	47	automatic	automatic	JJ
12235	20	48	subject	subject	JJ
12235	20	49	metadata	metadata	NN
12235	20	50	generation	generation	NN
12235	20	51	tool	tool	NN
12235	20	52	used	use	VBN
12235	20	53	for	for	IN
12235	20	54	this	this	DT
12235	20	55	project	project	NN
12235	20	56	,	,	,
12235	20	57	a	a	DT
12235	20	58	brief	brief	JJ
12235	20	59	background	background	NN
12235	20	60	of	of	IN
12235	20	61	“	"	``
12235	20	62	the	the	DT
12235	20	63	Long	Long	NNP
12235	20	64	-	-	HYPH
12235	20	65	S	S	NNP
12235	20	66	Problem	problem	NN
12235	20	67	,	,	,
12235	20	68	”	"	''
12235	20	69	and	and	CC
12235	20	70	the	the	DT
12235	20	71	distribution	distribution	NN
12235	20	72	of	of	IN
12235	20	73	encyclopedia	encyclopedia	JJ
12235	20	74	entry	entry	NN
12235	20	75	lengths	length	NNS
12235	20	76	in	in	IN
12235	20	77	the	the	DT
12235	20	78	3rd	3rd	JJ
12235	20	79	edition	edition	NN
12235	20	80	.	.	.
12235	21	1	The	the	DT
12235	21	2	background	background	NN
12235	21	3	section	section	NN
12235	21	4	will	will	MD
12235	21	5	be	be	VB
12235	21	6	followed	follow	VBN
12235	21	7	by	by	IN
12235	21	8	research	research	NN
12235	21	9	objectives	objective	NNS
12235	21	10	and	and	CC
12235	21	11	method	method	NN
12235	21	12	supporting	support	VBG
12235	21	13	the	the	DT
12235	21	14	analysis	analysis	NN
12235	21	15	.	.	.
12235	22	1	Next	next	RB
12235	22	2	,	,	,
12235	22	3	the	the	DT
12235	22	4	results	result	NNS
12235	22	5	are	be	VBP
12235	22	6	presented	present	VBN
12235	22	7	,	,	,
12235	22	8	demonstrating	demonstrate	VBG
12235	22	9	prevalence	prevalence	NN
12235	22	10	of	of	IN
12235	22	11	terms	term	NNS
12235	22	12	omitted	omit	VBN
12235	22	13	from	from	IN
12235	22	14	the	the	DT
12235	22	15	automatic	automatic	JJ
12235	22	16	subject	subject	JJ
12235	22	17	metadata	metadata	NN
12235	22	18	generation	generation	NN
12235	22	19	results	result	NNS
12235	22	20	if	if	IN
12235	22	21	the	the	DT
12235	22	22	Long	Long	NNP
12235	22	23	-	-	HYPH
12235	22	24	S	S	NNP
12235	22	25	is	be	VBZ
12235	22	26	not	not	RB
12235	22	27	corrected	correct	VBN
12235	22	28	to	to	IN
12235	22	29	a	a	DT
12235	22	30	standard	standard	JJ
12235	22	31	small	small	JJ
12235	22	32	<	<	XX
12235	22	33	s	s	NNP
12235	22	34	>	>	XX
12235	22	35	character	character	NN
12235	22	36	,	,	,
12235	22	37	as	as	RB
12235	22	38	well	well	RB
12235	22	39	as	as	IN
12235	22	40	the	the	DT
12235	22	41	impact	impact	NN
12235	22	42	of	of	IN
12235	22	43	encyclopedia	encyclopedia	NNS
12235	22	44	entry	entry	NN
12235	22	45	length	length	NN
12235	22	46	upon	upon	IN
12235	22	47	these	these	DT
12235	22	48	results	result	NNS
12235	22	49	.	.	.
12235	23	1	The	the	DT
12235	23	2	results	result	NNS
12235	23	3	are	be	VBP
12235	23	4	followed	follow	VBN
12235	23	5	by	by	IN
12235	23	6	a	a	DT
12235	23	7	contextual	contextual	JJ
12235	23	8	discussion	discussion	NN
12235	23	9	,	,	,
12235	23	10	and	and	CC
12235	23	11	a	a	DT
12235	23	12	conclusion	conclusion	NN
12235	23	13	that	that	WDT
12235	23	14	highlights	highlight	VBZ
12235	23	15	key	key	JJ
12235	23	16	findings	finding	NNS
12235	23	17	and	and	CC
12235	23	18	identifies	identify	VBZ
12235	23	19	future	future	JJ
12235	23	20	research	research	NN
12235	23	21	.	.	.
12235	24	1	BACKGROUND	background	NN
12235	24	2	Indexing	index	VBG
12235	24	3	for	for	IN
12235	24	4	the	the	DT
12235	24	5	19th	19th	JJ
12235	24	6	-	-	HYPH
12235	24	7	Century	Century	NNP
12235	24	8	Knowledge	Knowledge	NNP
12235	24	9	Project	Project	NNP
12235	24	10	The	the	DT
12235	24	11	19th	19th	JJ
12235	24	12	-	-	HYPH
12235	24	13	Century	Century	NNP
12235	24	14	Knowledge	Knowledge	NNP
12235	24	15	Project	Project	NNP
12235	24	16	,	,	,
12235	24	17	an	an	DT
12235	24	18	NEH	NEH	NNP
12235	24	19	-	-	HYPH
12235	24	20	funded	fund	VBN
12235	24	21	initiative	initiative	NN
12235	24	22	at	at	IN
12235	24	23	Temple	Temple	NNP
12235	24	24	University	University	NNP
12235	24	25	,	,	,
12235	24	26	is	be	VBZ
12235	24	27	fully	fully	RB
12235	24	28	digitizing	digitize	VBG
12235	24	29	four	four	CD
12235	24	30	historical	historical	JJ
12235	24	31	editions	edition	NNS
12235	24	32	of	of	IN
12235	24	33	the	the	DT
12235	24	34	Encyclopedia	Encyclopedia	NNP
12235	24	35	Britannica	Britannica	NNP
12235	24	36	(	(	-LRB-
12235	24	37	the	the	DT
12235	24	38	3rd	3rd	JJ
12235	24	39	,	,	,
12235	24	40	7th	7th	JJ
12235	24	41	,	,	,
12235	24	42	9th	9th	JJ
12235	24	43	,	,	,
12235	24	44	and	and	CC
12235	24	45	11th	11th	NN
12235	24	46	)	)	-RRB-
12235	24	47	.	.	.
12235	25	1	The	the	DT
12235	25	2	long	long	JJ
12235	25	3	-	-	HYPH
12235	25	4	term	term	NN
12235	25	5	goal	goal	NN
12235	25	6	of	of	IN
12235	25	7	the	the	DT
12235	25	8	project	project	NN
12235	25	9	is	be	VBZ
12235	25	10	to	to	TO
12235	25	11	analyze	analyze	VB
12235	25	12	the	the	DT
12235	25	13	evolving	evolve	VBG
12235	25	14	conceptualization	conceptualization	NN
12235	25	15	of	of	IN
12235	25	16	knowledge	knowledge	NN
12235	25	17	across	across	IN
12235	25	18	the	the	DT
12235	25	19	19th	19th	JJ
12235	25	20	century.5	century.5	.
12235	25	21	The	the	DT
12235	25	22	3rd	3rd	JJ
12235	25	23	edition	edition	NN
12235	25	24	of	of	IN
12235	25	25	the	the	DT
12235	25	26	Encyclopedia	Encyclopedia	NNP
12235	25	27	Britannica	Britannica	NNP
12235	25	28	(	(	-LRB-
12235	25	29	1797	1797	CD
12235	25	30	)	)	-RRB-
12235	25	31	is	be	VBZ
12235	25	32	the	the	DT
12235	25	33	earliest	early	JJS
12235	25	34	edition	edition	NN
12235	25	35	being	be	VBG
12235	25	36	digitized	digitize	VBN
12235	25	37	for	for	IN
12235	25	38	this	this	DT
12235	25	39	project	project	NN
12235	25	40	.	.	.
12235	26	1	The	the	DT
12235	26	2	3rd	3rd	JJ
12235	26	3	edition	edition	NN
12235	26	4	consists	consist	VBZ
12235	26	5	of	of	IN
12235	26	6	18	18	CD
12235	26	7	volumes	volume	NNS
12235	26	8	,	,	,
12235	26	9	with	with	IN
12235	26	10	a	a	DT
12235	26	11	total	total	NN
12235	26	12	of	of	IN
12235	26	13	14,579	14,579	CD
12235	26	14	pages	page	NNS
12235	26	15	,	,	,
12235	26	16	and	and	CC
12235	26	17	individual	individual	JJ
12235	26	18	entries	entry	NNS
12235	26	19	ranging	range	VBG
12235	26	20	from	from	IN
12235	26	21	four	four	CD
12235	26	22	to	to	IN
12235	26	23	over	over	IN
12235	26	24	150,000	150,000	CD
12235	26	25	words	word	NNS
12235	26	26	.	.	.
12235	27	1	For	for	IN
12235	27	2	each	each	DT
12235	27	3	individual	individual	JJ
12235	27	4	entry	entry	NN
12235	27	5	,	,	,
12235	27	6	researchers	researcher	NNS
12235	27	7	at	at	IN
12235	27	8	Temple	Temple	NNP
12235	27	9	have	have	VBP
12235	27	10	created	create	VBN
12235	27	11	individual	individual	JJ
12235	27	12	TEI	tei	NN
12235	27	13	-	-	HYPH
12235	27	14	XML	xml	NN
12235	27	15	files	file	NNS
12235	27	16	from	from	IN
12235	27	17	the	the	DT
12235	27	18	OCR	OCR	NNP
12235	27	19	output	output	NN
12235	27	20	.	.	.
12235	28	1	In	in	IN
12235	28	2	order	order	NN
12235	28	3	to	to	TO
12235	28	4	enrich	enrich	VB
12235	28	5	accessibility	accessibility	NN
12235	28	6	and	and	CC
12235	28	7	analysis	analysis	NN
12235	28	8	across	across	IN
12235	28	9	this	this	DT
12235	28	10	digital	digital	JJ
12235	28	11	collection	collection	NN
12235	28	12	,	,	,
12235	28	13	The	the	DT
12235	28	14	Knowledge	Knowledge	NNP
12235	28	15	Project	Project	NNP
12235	28	16	will	will	MD
12235	28	17	be	be	VB
12235	28	18	adding	add	VBG
12235	28	19	controlled	control	VBN
12235	28	20	vocabulary	vocabulary	JJ
12235	28	21	subject	subject	JJ
12235	28	22	headings	heading	NNS
12235	28	23	into	into	IN
12235	28	24	the	the	DT
12235	28	25	TEI	tei	NN
12235	28	26	headers	header	NNS
12235	28	27	of	of	IN
12235	28	28	each	each	DT
12235	28	29	encyclopedia	encyclopedia	JJ
12235	28	30	entry	entry	NN
12235	28	31	XML	xml	NN
12235	28	32	file	file	NN
12235	28	33	.	.	.
12235	29	1	Considering	consider	VBG
12235	29	2	the	the	DT
12235	29	3	size	size	NN
12235	29	4	of	of	IN
12235	29	5	this	this	DT
12235	29	6	corpus	corpus	NN
12235	29	7	,	,	,
12235	29	8	both	both	CC
12235	29	9	in	in	IN
12235	29	10	terms	term	NNS
12235	29	11	of	of	IN
12235	29	12	entry	entry	NN
12235	29	13	length	length	NN
12235	29	14	and	and	CC
12235	29	15	number	number	NN
12235	29	16	of	of	IN
12235	29	17	entries	entry	NNS
12235	29	18	,	,	,
12235	29	19	automatic	automatic	JJ
12235	29	20	subject	subject	JJ
12235	29	21	metadata	metadata	NN
12235	29	22	generation	generation	NN
12235	29	23	will	will	MD
12235	29	24	be	be	VB
12235	29	25	required	require	VBN
12235	29	26	for	for	IN
12235	29	27	the	the	DT
12235	29	28	creation	creation	NN
12235	29	29	of	of	IN
12235	29	30	this	this	DT
12235	29	31	metadata	metadata	NN
12235	29	32	.	.	.
12235	30	1	The	the	DT
12235	30	2	Knowledge	Knowledge	NNP
12235	30	3	Project	Project	NNP
12235	30	4	will	will	MD
12235	30	5	employ	employ	VB
12235	30	6	controlled	control	VBN
12235	30	7	vocabularies	vocabulary	NNS
12235	30	8	to	to	TO
12235	30	9	replace	replace	VB
12235	30	10	or	or	CC
12235	30	11	complement	complement	NN
12235	30	12	naturally	naturally	RB
12235	30	13	extracted	extract	VBN
12235	30	14	keywords	keyword	NNS
12235	30	15	for	for	IN
12235	30	16	this	this	DT
12235	30	17	process	process	NN
12235	30	18	.	.	.
12235	31	1	Using	use	VBG
12235	31	2	controlled	control	VBN
12235	31	3	vocabularies	vocabulary	NNS
12235	31	4	adheres	adhere	NNS
12235	31	5	to	to	TO
12235	31	6	metadata	metadata	VB
12235	31	7	semantic	semantic	JJ
12235	31	8	interoperability	interoperability	NN
12235	31	9	best	good	JJS
12235	31	10	practices	practice	NNS
12235	31	11	,	,	,
12235	31	12	ensures	ensure	VBZ
12235	31	13	representation	representation	NN
12235	31	14	consistency	consistency	NN
12235	31	15	,	,	,
12235	31	16	and	and	CC
12235	31	17	helps	help	VBZ
12235	31	18	to	to	TO
12235	31	19	bypass	bypass	VB
12235	31	20	linguistic	linguistic	JJ
12235	31	21	idiosyncrasies	idiosyncrasy	NNS
12235	31	22	of	of	IN
12235	31	23	these	these	DT
12235	31	24	18th	18th	JJ
12235	31	25	and	and	CC
12235	31	26	19th	19th	JJ
12235	31	27	Century	Century	NNP
12235	31	28	primary	primary	JJ
12235	31	29	source	source	NN
12235	31	30	materials	material	NNS
12235	31	31	.	.	.
12235	32	1	6	6	CD
12235	32	2	We	-PRON-	PRP
12235	32	3	selected	select	VBD
12235	32	4	two	two	CD
12235	32	5	versions	version	NNS
12235	32	6	of	of	IN
12235	32	7	the	the	DT
12235	32	8	Library	Library	NNP
12235	32	9	of	of	IN
12235	32	10	Congress	Congress	NNP
12235	32	11	Subject	Subject	NNP
12235	32	12	Headings	Headings	NNPS
12235	32	13	(	(	-LRB-
12235	32	14	LCSH	LCSH	NNP
12235	32	15	)	)	-RRB-
12235	32	16	as	as	IN
12235	32	17	the	the	DT
12235	32	18	controlled	control	VBN
12235	32	19	vocabularies	vocabulary	NNS
12235	32	20	for	for	IN
12235	32	21	this	this	DT
12235	32	22	project	project	NN
12235	32	23	.	.	.
12235	33	1	LCSH	LCSH	NNP
12235	33	2	was	be	VBD
12235	33	3	selected	select	VBN
12235	33	4	due	due	IN
12235	33	5	to	to	IN
12235	33	6	its	-PRON-	PRP$
12235	33	7	relational	relational	JJ
12235	33	8	thesaurus	thesaurus	NN
12235	33	9	structure	structure	NN
12235	33	10	,	,	,
12235	33	11	multidisciplinary	multidisciplinary	JJ
12235	33	12	nature	nature	NN
12235	33	13	,	,	,
12235	33	14	and	and	CC
12235	33	15	continued	continue	VBN
12235	33	16	prevalence	prevalence	NN
12235	33	17	in	in	IN
12235	33	18	digital	digital	JJ
12235	33	19	collections	collection	NNS
12235	33	20	due	due	JJ
12235	33	21	to	to	IN
12235	33	22	its	-PRON-	PRP$
12235	33	23	expressiveness	expressiveness	NN
12235	33	24	and	and	CC
12235	33	25	status	status	NN
12235	33	26	as	as	IN
12235	33	27	the	the	DT
12235	33	28	largest	large	JJS
12235	33	29	general	general	JJ
12235	33	30	indexing	indexing	NN
12235	33	31	vocabulary.7	vocabulary.7	PDT
12235	33	32	In	in	IN
12235	33	33	addition	addition	NN
12235	33	34	to	to	IN
12235	33	35	the	the	DT
12235	33	36	headings	heading	NNS
12235	33	37	from	from	IN
12235	33	38	the	the	DT
12235	33	39	2018	2018	CD
12235	33	40	edition	edition	NN
12235	33	41	of	of	IN
12235	33	42	LCSH	LCSH	NNP
12235	33	43	,	,	,
12235	33	44	headings	heading	NNS
12235	33	45	from	from	IN
12235	33	46	the	the	DT
12235	33	47	1910	1910	CD
12235	33	48	LCSH	LCSH	NNP
12235	33	49	are	be	VBP
12235	33	50	also	also	RB
12235	33	51	implemented	implement	VBN
12235	33	52	in	in	IN
12235	33	53	order	order	NN
12235	33	54	to	to	TO
12235	33	55	provide	provide	VB
12235	33	56	a	a	DT
12235	33	57	more	more	RBR
12235	33	58	multi	multi	JJ
12235	33	59	-	-	JJ
12235	33	60	faceted	faceted	JJ
12235	33	61	representation	representation	NN
12235	33	62	,	,	,
12235	33	63	using	use	VBG
12235	33	64	temporally	temporally	RB
12235	33	65	-	-	HYPH
12235	33	66	relevant	relevant	JJ
12235	33	67	terms	term	NNS
12235	33	68	that	that	WDT
12235	33	69	may	may	MD
12235	33	70	have	have	VB
12235	33	71	been	be	VBN
12235	33	72	removed	remove	VBN
12235	33	73	from	from	IN
12235	33	74	the	the	DT
12235	33	75	contemporary	contemporary	JJ
12235	33	76	LCSH	LCSH	NNP
12235	33	77	.	.	.
12235	34	1	The	the	DT
12235	34	2	tool	tool	NN
12235	34	3	applied	apply	VBD
12235	34	4	for	for	IN
12235	34	5	this	this	DT
12235	34	6	process	process	NN
12235	34	7	is	be	VBZ
12235	34	8	HIVE	HIVE	NNP
12235	34	9	,	,	,
12235	34	10	a	a	DT
12235	34	11	vocabulary	vocabulary	JJ
12235	34	12	server	server	NN
12235	34	13	and	and	CC
12235	34	14	automatic	automatic	JJ
12235	34	15	indexing	indexing	NN
12235	34	16	application	application	NN
12235	34	17	.	.	.
12235	35	1	8	8	CD
12235	35	2	HIVE	hive	RB
12235	35	3	allows	allow	VBZ
12235	35	4	the	the	DT
12235	35	5	user	user	NN
12235	35	6	to	to	TO
12235	35	7	upload	upload	VB
12235	35	8	a	a	DT
12235	35	9	digital	digital	JJ
12235	35	10	text	text	NN
12235	35	11	or	or	CC
12235	35	12	URL	URL	NNP
12235	35	13	,	,	,
12235	35	14	select	select	VB
12235	35	15	one	one	CD
12235	35	16	or	or	CC
12235	35	17	more	more	JJR
12235	35	18	controlled	control	VBN
12235	35	19	vocabularies	vocabulary	NNS
12235	35	20	,	,	,
12235	35	21	and	and	CC
12235	35	22	performs	perform	VBZ
12235	35	23	automatic	automatic	JJ
12235	35	24	subject	subject	JJ
12235	35	25	indexing	indexing	NN
12235	35	26	through	through	IN
12235	35	27	the	the	DT
12235	35	28	mapping	mapping	NN
12235	35	29	of	of	IN
12235	35	30	naturally	naturally	RB
12235	35	31	extracted	extract	VBN
12235	35	32	keywords	keyword	NNS
12235	35	33	to	to	IN
12235	35	34	the	the	DT
12235	35	35	available	available	JJ
12235	35	36	controlled	control	VBN
12235	35	37	vocabulary	vocabulary	JJ
12235	35	38	terms	term	NNS
12235	35	39	.	.	.
12235	36	1	HIVE	HIVE	NNP
12235	36	2	was	be	VBD
12235	36	3	initially	initially	RB
12235	36	4	launched	launch	VBN
12235	36	5	as	as	IN
12235	36	6	an	an	DT
12235	36	7	IMLS	IMLS	NNP
12235	36	8	linked	link	VBN
12235	36	9	open	open	JJ
12235	36	10	INFORMATION	INFORMATION	NNP
12235	36	11	TECHNOLOGY	technology	NN
12235	36	12	AND	and	CC
12235	36	13	LIBRARIES	library	NNS
12235	36	14	SEPTEMBER	SEPTEMBER	NNP
12235	36	15	2020	2020	CD
12235	36	16	EVALUATING	evaluate	VBG
12235	36	17	THE	the	DT
12235	36	18	IMPACT	impact	NN
12235	36	19	OF	of	IN
12235	36	20	THE	the	DT
12235	36	21	LONG	long	JJ
12235	36	22	-	-	HYPH
12235	36	23	S	S	NNP
12235	36	24	|	|	NNP
12235	36	25	GRABUS	grabus	NN
12235	36	26	3	3	CD
12235	36	27	vocabulary	vocabulary	NN
12235	36	28	and	and	CC
12235	36	29	indexing	indexing	NN
12235	36	30	demonstration	demonstration	NN
12235	36	31	project	project	NN
12235	36	32	in	in	IN
12235	36	33	2009	2009	CD
12235	36	34	.	.	.
12235	37	1	Since	since	IN
12235	37	2	that	that	DT
12235	37	3	time	time	NN
12235	37	4	,	,	,
12235	37	5	HIVE	HIVE	NNP
12235	37	6	has	have	VBZ
12235	37	7	been	be	VBN
12235	37	8	further	further	RB
12235	37	9	developed	develop	VBN
12235	37	10	,	,	,
12235	37	11	with	with	IN
12235	37	12	the	the	DT
12235	37	13	addition	addition	NN
12235	37	14	of	of	IN
12235	37	15	more	more	JJR
12235	37	16	controlled	controlled	JJ
12235	37	17	vocabularies	vocabulary	NNS
12235	37	18	,	,	,
12235	37	19	user	user	NN
12235	37	20	interface	interface	NN
12235	37	21	options	option	NNS
12235	37	22	,	,	,
12235	37	23	and	and	CC
12235	37	24	the	the	DT
12235	37	25	RAKE	rake	NN
12235	37	26	keyword	keyword	NN
12235	37	27	extraction	extraction	NN
12235	37	28	algorithm	algorithm	NNP
12235	37	29	.	.	.
12235	38	1	The	the	DT
12235	38	2	RAKE	rake	NN
12235	38	3	keyword	keyword	NN
12235	38	4	extraction	extraction	NN
12235	38	5	algorithm	algorithm	NNP
12235	38	6	has	have	VBZ
12235	38	7	been	be	VBN
12235	38	8	selected	select	VBN
12235	38	9	for	for	IN
12235	38	10	this	this	DT
12235	38	11	project	project	NN
12235	38	12	after	after	IN
12235	38	13	a	a	DT
12235	38	14	comparison	comparison	NN
12235	38	15	of	of	IN
12235	38	16	topic	topic	NNP
12235	38	17	relevance	relevance	NNP
12235	38	18	precision	precision	NN
12235	38	19	scores	score	NNS
12235	38	20	for	for	IN
12235	38	21	three	three	CD
12235	38	22	keyword	keyword	NNP
12235	38	23	extraction	extraction	NN
12235	38	24	algorithms.9	algorithms.9	CD
12235	38	25	The	the	DT
12235	38	26	Long	Long	NNP
12235	38	27	-	-	HYPH
12235	38	28	S	S	NNP
12235	38	29	Problem	problem	NN
12235	38	30	Early	early	RB
12235	38	31	in	in	IN
12235	38	32	our	-PRON-	PRP$
12235	38	33	metadata	metadata	NN
12235	38	34	generation	generation	NN
12235	38	35	efforts	effort	NNS
12235	38	36	,	,	,
12235	38	37	we	-PRON-	PRP
12235	38	38	discovered	discover	VBD
12235	38	39	that	that	IN
12235	38	40	the	the	DT
12235	38	41	3rd	3rd	JJ
12235	38	42	edition	edition	NN
12235	38	43	of	of	IN
12235	38	44	the	the	DT
12235	38	45	Encyclopedia	Encyclopedia	NNP
12235	38	46	Britannica	Britannica	NNP
12235	38	47	employs	employ	VBZ
12235	38	48	the	the	DT
12235	38	49	historical	historical	JJ
12235	38	50	Long	Long	NNP
12235	38	51	-	-	HYPH
12235	38	52	S.	S.	NNP
12235	39	1	Originating	originate	VBG
12235	39	2	in	in	IN
12235	39	3	early	early	JJ
12235	39	4	Roman	roman	JJ
12235	39	5	cursive	cursive	NN
12235	39	6	script	script	NN
12235	39	7	,	,	,
12235	39	8	the	the	DT
12235	39	9	Long	Long	NNP
12235	39	10	-	-	HYPH
12235	39	11	S	S	NNP
12235	39	12	was	be	VBD
12235	39	13	used	use	VBN
12235	39	14	in	in	IN
12235	39	15	typesetting	typesetting	NN
12235	39	16	up	up	RP
12235	39	17	through	through	IN
12235	39	18	the	the	DT
12235	39	19	18th	18th	JJ
12235	39	20	century	century	NN
12235	39	21	,	,	,
12235	39	22	both	both	CC
12235	39	23	with	with	IN
12235	39	24	and	and	CC
12235	39	25	without	without	IN
12235	39	26	a	a	DT
12235	39	27	left	left	JJ
12235	39	28	crossbar	crossbar	NN
12235	39	29	.	.	.
12235	40	1	By	by	IN
12235	40	2	the	the	DT
12235	40	3	end	end	NN
12235	40	4	of	of	IN
12235	40	5	the	the	DT
12235	40	6	18th	18th	JJ
12235	40	7	century	century	NN
12235	40	8	,	,	,
12235	40	9	the	the	DT
12235	40	10	Long	Long	NNP
12235	40	11	-	-	HYPH
12235	40	12	S	S	NNP
12235	40	13	fell	fall	VBD
12235	40	14	out	out	IN
12235	40	15	of	of	IN
12235	40	16	use	use	NN
12235	40	17	with	with	IN
12235	40	18	printers.10	printers.10	NNP
12235	40	19	As	as	IN
12235	40	20	outlined	outline	VBN
12235	40	21	by	by	IN
12235	40	22	lexicographers	lexicographer	NNS
12235	40	23	of	of	IN
12235	40	24	the	the	DT
12235	40	25	17th	17th	JJ
12235	40	26	and	and	CC
12235	40	27	18th	18th	JJ
12235	40	28	centuries	century	NNS
12235	40	29	,	,	,
12235	40	30	the	the	DT
12235	40	31	rules	rule	NNS
12235	40	32	for	for	IN
12235	40	33	using	use	VBG
12235	40	34	the	the	DT
12235	40	35	Long	Long	NNP
12235	40	36	-	-	HYPH
12235	40	37	S	S	NNP
12235	40	38	were	be	VBD
12235	40	39	frequently	frequently	RB
12235	40	40	vague	vague	JJ
12235	40	41	,	,	,
12235	40	42	complicated	complicated	JJ
12235	40	43	,	,	,
12235	40	44	inconsistent	inconsistent	JJ
12235	40	45	over	over	IN
12235	40	46	time	time	NN
12235	40	47	,	,	,
12235	40	48	and	and	CC
12235	40	49	varied	vary	VBD
12235	40	50	according	accord	VBG
12235	40	51	to	to	IN
12235	40	52	language	language	NN
12235	40	53	(	(	-LRB-
12235	40	54	English	English	NNP
12235	40	55	,	,	,
12235	40	56	French	french	JJ
12235	40	57	,	,	,
12235	40	58	Spanish	spanish	JJ
12235	40	59	,	,	,
12235	40	60	or	or	CC
12235	40	61	Italian	Italian	NNP
12235	40	62	)	)	-RRB-
12235	40	63	.	.	.
12235	41	1	11	11	CD
12235	41	2	These	these	DT
12235	41	3	rules	rule	NNS
12235	41	4	specified	specify	VBD
12235	41	5	where	where	WRB
12235	41	6	in	in	IN
12235	41	7	a	a	DT
12235	41	8	word	word	NN
12235	41	9	the	the	DT
12235	41	10	Long	Long	NNP
12235	41	11	-	-	HYPH
12235	41	12	S	S	NNP
12235	41	13	should	should	MD
12235	41	14	be	be	VB
12235	41	15	used	use	VBN
12235	41	16	instead	instead	RB
12235	41	17	of	of	IN
12235	41	18	a	a	DT
12235	41	19	short	short	JJ
12235	41	20	<	<	XX
12235	41	21	s	s	NNP
12235	41	22	>	>	XX
12235	41	23	,	,	,
12235	41	24	whether	whether	IN
12235	41	25	it	-PRON-	PRP
12235	41	26	is	be	VBZ
12235	41	27	capitalized	capitalize	VBN
12235	41	28	,	,	,
12235	41	29	where	where	WRB
12235	41	30	it	-PRON-	PRP
12235	41	31	may	may	MD
12235	41	32	be	be	VB
12235	41	33	used	use	VBN
12235	41	34	in	in	IN
12235	41	35	proximity	proximity	NN
12235	41	36	to	to	IN
12235	41	37	apostrophes	apostrophe	NNS
12235	41	38	,	,	,
12235	41	39	hyphens	hyphen	NNS
12235	41	40	,	,	,
12235	41	41	and	and	CC
12235	41	42	the	the	DT
12235	41	43	letters	letter	NNS
12235	41	44	<	<	XX
12235	41	45	f	f	XX
12235	41	46	>	>	XX
12235	41	47	,	,	,
12235	41	48	<	<	XX
12235	41	49	b	b	NNP
12235	41	50	>	>	XX
12235	41	51	,	,	,
12235	41	52	<	<	XX
12235	41	53	h	h	NNP
12235	41	54	>	>	XX
12235	41	55	,	,	,
12235	41	56	and	and	CC
12235	41	57	<	<	XX
12235	41	58	k	k	NNP
12235	41	59	>	>	XX
12235	41	60	;	;	:
12235	41	61	and	and	CC
12235	41	62	whether	whether	IN
12235	41	63	it	-PRON-	PRP
12235	41	64	is	be	VBZ
12235	41	65	used	use	VBN
12235	41	66	as	as	IN
12235	41	67	part	part	NN
12235	41	68	of	of	IN
12235	41	69	a	a	DT
12235	41	70	compound	compound	NN
12235	41	71	word	word	NN
12235	41	72	or	or	CC
12235	41	73	abbreviation.12	abbreviation.12	NNP
12235	41	74	This	this	DT
12235	41	75	is	be	VBZ
12235	41	76	further	far	RBR
12235	41	77	complicated	complicate	VBN
12235	41	78	by	by	IN
12235	41	79	the	the	DT
12235	41	80	inclusion	inclusion	NN
12235	41	81	of	of	IN
12235	41	82	the	the	DT
12235	41	83	half	half	JJ
12235	41	84	-	-	HYPH
12235	41	85	crossbar	crossbar	NN
12235	41	86	,	,	,
12235	41	87	which	which	WDT
12235	41	88	occasionally	occasionally	RB
12235	41	89	results	result	VBZ
12235	41	90	in	in	IN
12235	41	91	two	two	CD
12235	41	92	consequences	consequence	NNS
12235	41	93	:	:	:
12235	41	94	(	(	-LRB-
12235	41	95	a	a	LS
12235	41	96	)	)	-RRB-
12235	41	97	The	the	DT
12235	41	98	Long	Long	NNP
12235	41	99	-	-	HYPH
12235	41	100	S	S	NNP
12235	41	101	may	may	MD
12235	41	102	be	be	VB
12235	41	103	interpreted	interpret	VBN
12235	41	104	by	by	IN
12235	41	105	OCR	OCR	NNP
12235	41	106	as	as	IN
12235	41	107	an	an	DT
12235	41	108	<	<	XX
12235	41	109	f	f	XX
12235	41	110	>	>	XX
12235	41	111	,	,	,
12235	41	112	and	and	CC
12235	41	113	<	<	XX
12235	41	114	b	b	NNP
12235	41	115	>	>	XX
12235	41	116	and	and	CC
12235	41	117	<	<	XX
12235	41	118	f	f	NNP
12235	41	119	>	>	XX
12235	41	120	may	may	MD
12235	41	121	be	be	VB
12235	41	122	interpreted	interpret	VBN
12235	41	123	by	by	IN
12235	41	124	OCR	OCR	NNP
12235	41	125	as	as	IN
12235	41	126	a	a	DT
12235	41	127	Long	Long	NNP
12235	41	128	-	-	HYPH
12235	41	129	S.	s.	NN
12235	42	1	Figure	figure	NN
12235	42	2	1	1	CD
12235	42	3	shows	show	VBZ
12235	42	4	an	an	DT
12235	42	5	example	example	NN
12235	42	6	from	from	IN
12235	42	7	the	the	DT
12235	42	8	3rd	3rd	JJ
12235	42	9	edition	edition	NN
12235	42	10	entry	entry	NN
12235	42	11	on	on	IN
12235	42	12	Russia	Russia	NNP
12235	42	13	,	,	,
12235	42	14	in	in	IN
12235	42	15	which	which	WDT
12235	42	16	the	the	DT
12235	42	17	original	original	JJ
12235	42	18	text	text	NN
12235	42	19	specifies	specify	VBZ
12235	42	20	“	"	``
12235	42	21	of	of	IN
12235	42	22	”	"	''
12235	42	23	(	(	-LRB-
12235	42	24	line	line	NN
12235	42	25	1	1	CD
12235	42	26	in	in	IN
12235	42	27	top	top	JJ
12235	42	28	figure	figure	NN
12235	42	29	)	)	-RRB-
12235	42	30	,	,	,
12235	42	31	yet	yet	CC
12235	42	32	the	the	DT
12235	42	33	OCR	OCR	NNP
12235	42	34	output	output	NN
12235	42	35	has	have	VBZ
12235	42	36	interpreted	interpret	VBN
12235	42	37	the	the	DT
12235	42	38	character	character	NN
12235	42	39	as	as	IN
12235	42	40	a	a	DT
12235	42	41	Long	Long	NNP
12235	42	42	-	-	HYPH
12235	42	43	S.	s.	NN
12235	43	1	The	the	DT
12235	43	2	Long	Long	NNP
12235	43	3	-	-	HYPH
12235	43	4	S	S	NNP
12235	43	5	may	may	MD
12235	43	6	also	also	RB
12235	43	7	occasionally	occasionally	RB
12235	43	8	be	be	VB
12235	43	9	interpreted	interpret	VBN
12235	43	10	by	by	IN
12235	43	11	the	the	DT
12235	43	12	OCR	OCR	NNP
12235	43	13	as	as	IN
12235	43	14	a	a	DT
12235	43	15	lower-	lower-	JJ
12235	43	16	case	case	NN
12235	43	17	<	<	XX
12235	43	18	l	l	NNP
12235	43	19	>	>	XX
12235	43	20	,	,	,
12235	43	21	such	such	JJ
12235	43	22	as	as	IN
12235	43	23	the	the	DT
12235	43	24	“	"	``
12235	43	25	univerlity	univerlity	NN
12235	43	26	of	of	IN
12235	43	27	Dublin	Dublin	NNP
12235	43	28	”	"	''
12235	43	29	in	in	IN
12235	43	30	the	the	DT
12235	43	31	3rd	3rd	JJ
12235	43	32	edition	edition	NN
12235	43	33	entry	entry	NN
12235	43	34	on	on	IN
12235	43	35	Robinson	Robinson	NNP
12235	43	36	(	(	-LRB-
12235	43	37	The	the	DT
12235	43	38	most	most	RBS
12235	43	39	Rev	Rev	NNP
12235	43	40	Sir	Sir	NNP
12235	43	41	Richard	Richard	NNP
12235	43	42	)	)	-RRB-
12235	43	43	.	.	.
12235	44	1	These	these	DT
12235	44	2	complications	complication	NNS
12235	44	3	and	and	CC
12235	44	4	inconsistencies	inconsistency	NNS
12235	44	5	are	be	VBP
12235	44	6	challenges	challenge	NNS
12235	44	7	when	when	WRB
12235	44	8	developing	develop	VBG
12235	44	9	Python	Python	NNP
12235	44	10	rules	rule	NNS
12235	44	11	for	for	IN
12235	44	12	correcting	correct	VBG
12235	44	13	the	the	DT
12235	44	14	Long	Long	NNP
12235	44	15	-	-	HYPH
12235	44	16	S	S	NNP
12235	44	17	in	in	IN
12235	44	18	an	an	DT
12235	44	19	automated	automate	VBN
12235	44	20	way	way	NN
12235	44	21	,	,	,
12235	44	22	and	and	CC
12235	44	23	even	even	RB
12235	44	24	preexisting	preexist	VBG
12235	44	25	scripts	script	NNS
12235	44	26	will	will	MD
12235	44	27	need	need	VB
12235	44	28	to	to	TO
12235	44	29	be	be	VB
12235	44	30	adapted	adapt	VBN
12235	44	31	for	for	IN
12235	44	32	individual	individual	JJ
12235	44	33	use	use	NN
12235	44	34	with	with	IN
12235	44	35	a	a	DT
12235	44	36	particular	particular	JJ
12235	44	37	corpus	corpus	NN
12235	44	38	.	.	.
12235	45	1	Figure	figure	NN
12235	45	2	1	1	CD
12235	45	3	.	.	.
12235	46	1	Example	example	NN
12235	46	2	from	from	IN
12235	46	3	the	the	DT
12235	46	4	3rd	3rd	JJ
12235	46	5	edition	edition	NN
12235	46	6	entry	entry	NN
12235	46	7	on	on	IN
12235	46	8	Russia	Russia	NNP
12235	46	9	,	,	,
12235	46	10	comparing	compare	VBG
12235	46	11	the	the	DT
12235	46	12	original	original	JJ
12235	46	13	use	use	NN
12235	46	14	of	of	IN
12235	46	15	a	a	DT
12235	46	16	letter	letter	NN
12235	46	17	<	<	XX
12235	46	18	f	f	XX
12235	46	19	>	>	XX
12235	46	20	in	in	IN
12235	46	21	“	"	``
12235	46	22	of	of	IN
12235	46	23	”	"	''
12235	46	24	to	to	IN
12235	46	25	the	the	DT
12235	46	26	OCR	OCR	NNP
12235	46	27	output	output	NN
12235	46	28	of	of	IN
12235	46	29	the	the	DT
12235	46	30	same	same	JJ
12235	46	31	passage	passage	NN
12235	46	32	,	,	,
12235	46	33	which	which	WDT
12235	46	34	mistakenly	mistakenly	RB
12235	46	35	interprets	interpret	VBZ
12235	46	36	the	the	DT
12235	46	37	character	character	NN
12235	46	38	as	as	IN
12235	46	39	a	a	DT
12235	46	40	Long	Long	NNP
12235	46	41	-	-	HYPH
12235	46	42	S.	s.	NN
12235	46	43	INFORMATION	INFORMATION	NNP
12235	46	44	TECHNOLOGY	technology	NN
12235	46	45	AND	and	CC
12235	46	46	LIBRARIES	library	NNS
12235	46	47	SEPTEMBER	SEPTEMBER	NNP
12235	46	48	2020	2020	CD
12235	46	49	EVALUATING	evaluate	VBG
12235	46	50	THE	the	DT
12235	46	51	IMPACT	impact	NN
12235	46	52	OF	of	IN
12235	46	53	THE	the	DT
12235	46	54	LONG	long	JJ
12235	46	55	-	-	HYPH
12235	46	56	S	s	NN
12235	46	57	|	|	NNP
12235	46	58	GRABUS	grabus	NN
12235	46	59	4	4	CD
12235	46	60	Despite	despite	IN
12235	46	61	the	the	DT
12235	46	62	transition	transition	NN
12235	46	63	away	away	RB
12235	46	64	from	from	IN
12235	46	65	the	the	DT
12235	46	66	Long	Long	NNP
12235	46	67	-	-	HYPH
12235	46	68	S	S	NNP
12235	46	69	towards	towards	IN
12235	46	70	the	the	DT
12235	46	71	end	end	NN
12235	46	72	of	of	IN
12235	46	73	the	the	DT
12235	46	74	18th	18th	JJ
12235	46	75	century	century	NN
12235	46	76	,	,	,
12235	46	77	the	the	DT
12235	46	78	3rd	3rd	JJ
12235	46	79	edition	edition	NN
12235	46	80	of	of	IN
12235	46	81	the	the	DT
12235	46	82	Encyclopedia	Encyclopedia	NNP
12235	46	83	Britannica	Britannica	NNP
12235	46	84	(	(	-LRB-
12235	46	85	published	publish	VBN
12235	46	86	in	in	IN
12235	46	87	1797	1797	CD
12235	46	88	)	)	-RRB-
12235	46	89	implements	implement	VBZ
12235	46	90	the	the	DT
12235	46	91	Long	Long	NNP
12235	46	92	-	-	HYPH
12235	46	93	S	S	NNP
12235	46	94	throughout	throughout	IN
12235	46	95	,	,	,
12235	46	96	with	with	IN
12235	46	97	approximately	approximately	RB
12235	46	98	100,594	100,594	CD
12235	46	99	instances	instance	NNS
12235	46	100	of	of	IN
12235	46	101	the	the	DT
12235	46	102	Long	Long	NNP
12235	46	103	-	-	HYPH
12235	46	104	S	S	NNP
12235	46	105	in	in	IN
12235	46	106	the	the	DT
12235	46	107	OCR	OCR	NNP
12235	46	108	output	output	NN
12235	46	109	.	.	.
12235	47	1	When	when	WRB
12235	47	2	performing	perform	VBG
12235	47	3	metadata	metadata	NN
12235	47	4	generation	generation	NN
12235	47	5	with	with	IN
12235	47	6	the	the	DT
12235	47	7	HIVE	HIVE	NNP
12235	47	8	tool	tool	NN
12235	47	9	on	on	IN
12235	47	10	the	the	DT
12235	47	11	OCR	OCR	NNP
12235	47	12	output	output	NN
12235	47	13	for	for	IN
12235	47	14	an	an	DT
12235	47	15	entry	entry	NN
12235	47	16	,	,	,
12235	47	17	the	the	DT
12235	47	18	Long	Long	NNP
12235	47	19	-	-	HYPH
12235	47	20	S	S	NNP
12235	47	21	is	be	VBZ
12235	47	22	most	most	RBS
12235	47	23	often	often	RB
12235	47	24	interpreted	interpret	VBN
12235	47	25	by	by	IN
12235	47	26	the	the	DT
12235	47	27	automatic	automatic	JJ
12235	47	28	metadata	metadata	NN
12235	47	29	generation	generation	NN
12235	47	30	tool	tool	NN
12235	47	31	as	as	IN
12235	47	32	an	an	DT
12235	47	33	<	<	XX
12235	47	34	f	f	XX
12235	47	35	>	>	XX
12235	47	36	,	,	,
12235	47	37	which	which	WDT
12235	47	38	can	can	MD
12235	47	39	result	result	VB
12235	47	40	in	in	IN
12235	47	41	(	(	-LRB-
12235	47	42	a	a	DT
12235	47	43	)	)	-RRB-
12235	47	44	inaccurate	inaccurate	JJ
12235	47	45	keyword	keyword	NN
12235	47	46	extraction	extraction	NN
12235	47	47	(	(	-LRB-
12235	47	48	e.g.	e.g.	RB
12235	47	49	,	,	,
12235	47	50	Russians→	russians→	JJ
12235	47	51	Ruffians	Ruffians	NNPS
12235	47	52	)	)	-RRB-
12235	47	53	,	,	,
12235	47	54	and	and	CC
12235	47	55	(	(	-LRB-
12235	47	56	b	b	NN
12235	47	57	)	)	-RRB-
12235	47	58	when	when	WRB
12235	47	59	mapping	mapping	NN
12235	47	60	extracted	extract	VBD
12235	47	61	keywords	keyword	NNS
12235	47	62	to	to	IN
12235	47	63	controlled	controlled	JJ
12235	47	64	vocabulary	vocabulary	JJ
12235	47	65	terms	term	NNS
12235	47	66	,	,	,
12235	47	67	essential	essential	JJ
12235	47	68	topics	topic	NNS
12235	47	69	could	could	MD
12235	47	70	be	be	VB
12235	47	71	unidentifiable	unidentifiable	JJ
12235	47	72	,	,	,
12235	47	73	and	and	CC
12235	47	74	HIVE	HIVE	NNP
12235	47	75	will	will	MD
12235	47	76	subsequently	subsequently	RB
12235	47	77	omit	omit	VB
12235	47	78	them	-PRON-	PRP
12235	47	79	from	from	IN
12235	47	80	the	the	DT
12235	47	81	results	result	NNS
12235	47	82	because	because	IN
12235	47	83	they	-PRON-	PRP
12235	47	84	can	can	MD
12235	47	85	not	not	RB
12235	47	86	be	be	VB
12235	47	87	mapped	map	VBN
12235	47	88	to	to	IN
12235	47	89	controlled	control	VBN
12235	47	90	vocabulary	vocabulary	JJ
12235	47	91	terms	term	NNS
12235	47	92	.	.	.
12235	48	1	Figure	figure	NN
12235	48	2	2	2	CD
12235	48	3	provides	provide	VBZ
12235	48	4	a	a	DT
12235	48	5	truncated	truncated	JJ
12235	48	6	view	view	NN
12235	48	7	of	of	IN
12235	48	8	Long	long	JJ
12235	48	9	-	-	HYPH
12235	48	10	S	S	NNP
12235	48	11	words	word	NNS
12235	48	12	in	in	IN
12235	48	13	the	the	DT
12235	48	14	3rd	3rd	JJ
12235	48	15	edition	edition	NN
12235	48	16	entry	entry	NN
12235	48	17	on	on	IN
12235	48	18	Rum	Rum	NNP
12235	48	19	,	,	,
12235	48	20	which	which	WDT
12235	48	21	are	be	VBP
12235	48	22	subsequently	subsequently	RB
12235	48	23	removed	remove	VBN
12235	48	24	from	from	IN
12235	48	25	the	the	DT
12235	48	26	pool	pool	NN
12235	48	27	of	of	IN
12235	48	28	automatically	automatically	RB
12235	48	29	extracted	extract	VBN
12235	48	30	keywords	keyword	NNS
12235	48	31	when	when	WRB
12235	48	32	performing	perform	VBG
12235	48	33	the	the	DT
12235	48	34	automatic	automatic	JJ
12235	48	35	subject	subject	JJ
12235	48	36	indexing	indexing	NN
12235	48	37	sequence	sequence	NN
12235	48	38	in	in	IN
12235	48	39	HIVE	HIVE	NNP
12235	48	40	.	.	.
12235	49	1	Using	use	VBG
12235	49	2	keyword	keyword	NNP
12235	49	3	extraction	extraction	NN
12235	49	4	algorithms	algorithm	NNS
12235	49	5	that	that	WDT
12235	49	6	are	be	VBP
12235	49	7	largely	largely	RB
12235	49	8	dependent	dependent	JJ
12235	49	9	upon	upon	IN
12235	49	10	term	term	NN
12235	49	11	frequencies	frequency	NNS
12235	49	12	,	,	,
12235	49	13	automatic	automatic	JJ
12235	49	14	subject	subject	NN
12235	49	15	indexing	indexing	NN
12235	49	16	for	for	IN
12235	49	17	an	an	DT
12235	49	18	entry	entry	NN
12235	49	19	on	on	IN
12235	49	20	Rum	Rum	NNP
12235	49	21	may	may	MD
12235	49	22	be	be	VB
12235	49	23	substantially	substantially	RB
12235	49	24	hindered	hinder	VBN
12235	49	25	when	when	WRB
12235	49	26	meaningful	meaningful	JJ
12235	49	27	and	and	CC
12235	49	28	frequently	frequently	RB
12235	49	29	occurring	occur	VBG
12235	49	30	words	word	NNS
12235	49	31	such	such	JJ
12235	49	32	as	as	IN
12235	49	33	sugar	sugar	NN
12235	49	34	,	,	,
12235	49	35	and	and	CC
12235	49	36	yeast	yeast	NN
12235	49	37	are	be	VBP
12235	49	38	removed	remove	VBN
12235	49	39	.	.	.
12235	50	1	Figure	figure	NN
12235	50	2	2	2	CD
12235	50	3	.	.	.
12235	51	1	Examples	example	NNS
12235	51	2	of	of	IN
12235	51	3	the	the	DT
12235	51	4	Long	Long	NNP
12235	51	5	-	-	HYPH
12235	51	6	S	S	NNP
12235	51	7	in	in	IN
12235	51	8	the	the	DT
12235	51	9	3rd	3rd	JJ
12235	51	10	edition	edition	NN
12235	51	11	Encyclopedia	Encyclopedia	NNP
12235	51	12	Britannica	Britannica	NNP
12235	51	13	entry	entry	NN
12235	51	14	on	on	IN
12235	51	15	Rum	Rum	NNP
12235	51	16	.	.	.
12235	52	1	Using	use	VBG
12235	52	2	this	this	DT
12235	52	3	example	example	NN
12235	52	4	entry	entry	NN
12235	52	5	,	,	,
12235	52	6	the	the	DT
12235	52	7	automatic	automatic	JJ
12235	52	8	subject	subject	JJ
12235	52	9	indexing	indexing	NN
12235	52	10	results	result	NNS
12235	52	11	were	be	VBD
12235	52	12	compared	compare	VBN
12235	52	13	using	use	VBG
12235	52	14	Python	Python	NNP
12235	52	15	,	,	,
12235	52	16	to	to	TO
12235	52	17	determine	determine	VB
12235	52	18	which	which	WDT
12235	52	19	terms	term	NNS
12235	52	20	only	only	RB
12235	52	21	appear	appear	VBP
12235	52	22	when	when	WRB
12235	52	23	the	the	DT
12235	52	24	Long	Long	NNP
12235	52	25	-	-	HYPH
12235	52	26	S	S	NNP
12235	52	27	has	have	VBZ
12235	52	28	been	be	VBN
12235	52	29	corrected	correct	VBN
12235	52	30	to	to	IN
12235	52	31	the	the	DT
12235	52	32	standard	standard	NN
12235	52	33	<	<	XX
12235	52	34	s	s	NNP
12235	52	35	>	>	XX
12235	52	36	.	.	.
12235	53	1	The	the	DT
12235	53	2	comparison	comparison	NN
12235	53	3	showed	show	VBD
12235	53	4	that	that	IN
12235	53	5	16	16	CD
12235	53	6	total	total	JJ
12235	53	7	terms	term	NNS
12235	53	8	no	no	RB
12235	53	9	longer	long	RBR
12235	53	10	appeared	appear	VBD
12235	53	11	in	in	IN
12235	53	12	the	the	DT
12235	53	13	results	result	NNS
12235	53	14	when	when	WRB
12235	53	15	the	the	DT
12235	53	16	Long	Long	NNP
12235	53	17	-	-	HYPH
12235	53	18	S	S	NNP
12235	53	19	was	be	VBD
12235	53	20	not	not	RB
12235	53	21	corrected	correct	VBN
12235	53	22	to	to	IN
12235	53	23	a	a	DT
12235	53	24	standard	standard	NN
12235	53	25	<	<	XX
12235	53	26	s	s	NNP
12235	53	27	>	>	XX
12235	53	28	:	:	:
12235	53	29	ten	ten	CD
12235	53	30	terms	term	NNS
12235	53	31	using	use	VBG
12235	53	32	the	the	DT
12235	53	33	2018	2018	CD
12235	53	34	LCSH	LCSH	NNP
12235	53	35	,	,	,
12235	53	36	and	and	CC
12235	53	37	six	six	CD
12235	53	38	terms	term	NNS
12235	53	39	using	use	VBG
12235	53	40	the	the	DT
12235	53	41	1910	1910	CD
12235	53	42	LCSH	LCSH	NNP
12235	53	43	.	.	.
12235	54	1	These	these	DT
12235	54	2	omitted	omit	VBN
12235	54	3	results	result	NNS
12235	54	4	included	include	VBD
12235	54	5	the	the	DT
12235	54	6	terms	term	NNS
12235	54	7	sugar	sugar	NN
12235	54	8	and	and	CC
12235	54	9	yeast	yeast	NN
12235	54	10	.	.	.
12235	55	1	The	the	DT
12235	55	2	next	next	JJ
12235	55	3	section	section	NN
12235	55	4	will	will	MD
12235	55	5	discuss	discuss	VB
12235	55	6	the	the	DT
12235	55	7	encyclopedia	encyclopedia	NN
12235	55	8	entry	entry	NN
12235	55	9	word	word	NN
12235	55	10	count	count	NN
12235	55	11	for	for	IN
12235	55	12	this	this	DT
12235	55	13	corpus	corpus	NN
12235	55	14	,	,	,
12235	55	15	and	and	CC
12235	55	16	the	the	DT
12235	55	17	possible	possible	JJ
12235	55	18	impact	impact	NN
12235	55	19	that	that	IN
12235	55	20	this	this	DT
12235	55	21	may	may	MD
12235	55	22	have	have	VB
12235	55	23	upon	upon	IN
12235	55	24	automatic	automatic	JJ
12235	55	25	subject	subject	JJ
12235	55	26	indexing	indexing	NN
12235	55	27	between	between	IN
12235	55	28	corrected	corrected	JJ
12235	55	29	and	and	CC
12235	55	30	uncorrected	uncorrecte	VBD
12235	55	31	Long	Long	NNP
12235	55	32	-	-	HYPH
12235	55	33	S	S	NNP
12235	55	34	instances	instance	NNS
12235	55	35	.	.	.
12235	56	1	Encyclopedia	encyclopedia	NN
12235	56	2	Entry	entry	NN
12235	56	3	Lengths	length	VBZ
12235	56	4	Consistent	Consistent	NNP
12235	56	5	with	with	IN
12235	56	6	other	other	JJ
12235	56	7	Encyclopedia	Encyclopedia	NNP
12235	56	8	Britannica	Britannica	NNP
12235	56	9	editions	edition	NNS
12235	56	10	in	in	IN
12235	56	11	the	the	DT
12235	56	12	18th	18th	JJ
12235	56	13	and	and	CC
12235	56	14	19th	19th	JJ
12235	56	15	centuries	century	NNS
12235	56	16	,	,	,
12235	56	17	the	the	DT
12235	56	18	encyclopedia	encyclopedia	JJ
12235	56	19	entries	entry	NNS
12235	56	20	in	in	IN
12235	56	21	the	the	DT
12235	56	22	3rd	3rd	JJ
12235	56	23	edition	edition	NN
12235	56	24	vary	vary	VBP
12235	56	25	substantially	substantially	RB
12235	56	26	in	in	IN
12235	56	27	length	length	NN
12235	56	28	.	.	.
12235	57	1	A	a	DT
12235	57	2	convenience	convenience	NN
12235	57	3	sample	sample	NN
12235	57	4	of	of	IN
12235	57	5	3,849	3,849	CD
12235	57	6	3rd	3rd	JJ
12235	57	7	edition	edition	NN
12235	57	8	entries	entry	NNS
12235	57	9	ranging	range	VBG
12235	57	10	in	in	IN
12235	57	11	length	length	NN
12235	57	12	from	from	IN
12235	57	13	2	2	CD
12235	57	14	to	to	IN
12235	57	15	202,848	202,848	CD
12235	57	16	words	word	NNS
12235	57	17	demonstrated	demonstrate	VBD
12235	57	18	an	an	DT
12235	57	19	arithmetic	arithmetic	JJ
12235	57	20	mean	mean	NN
12235	57	21	of	of	IN
12235	57	22	INFORMATION	INFORMATION	NNP
12235	57	23	TECHNOLOGY	TECHNOLOGY	NNP
12235	57	24	AND	and	CC
12235	57	25	LIBRARIES	library	NNS
12235	57	26	SEPTEMBER	SEPTEMBER	NNP
12235	57	27	2020	2020	CD
12235	57	28	EVALUATING	evaluate	VBG
12235	57	29	THE	the	DT
12235	57	30	IMPACT	impact	NN
12235	57	31	OF	of	IN
12235	57	32	THE	the	DT
12235	57	33	LONG	long	JJ
12235	57	34	-	-	HYPH
12235	57	35	S	S	NNP
12235	57	36	|	|	NNP
12235	57	37	GRABUS	grabus	NN
12235	57	38	5	5	CD
12235	57	39	826.60	826.60	CD
12235	57	40	,	,	,
12235	57	41	and	and	CC
12235	57	42	a	a	DT
12235	57	43	median	median	JJ
12235	57	44	word	word	NN
12235	57	45	count	count	NN
12235	57	46	of	of	IN
12235	57	47	71	71	CD
12235	57	48	.	.	.
12235	58	1	As	as	IN
12235	58	2	shown	show	VBN
12235	58	3	in	in	IN
12235	58	4	figure	figure	NN
12235	58	5	3	3	CD
12235	58	6	,	,	,
12235	58	7	this	this	DT
12235	58	8	indicates	indicate	VBZ
12235	58	9	a	a	DT
12235	58	10	significant	significant	JJ
12235	58	11	skew	skew	NN
12235	58	12	towards	towards	IN
12235	58	13	shorter	short	JJR
12235	58	14	entry	entry	NN
12235	58	15	lengths	length	NNS
12235	58	16	.	.	.
12235	59	1	For	for	IN
12235	59	2	the	the	DT
12235	59	3	vast	vast	JJ
12235	59	4	majority	majority	NN
12235	59	5	of	of	IN
12235	59	6	encyclopedia	encyclopedia	JJ
12235	59	7	entries	entry	NNS
12235	59	8	in	in	IN
12235	59	9	this	this	DT
12235	59	10	corpus	corpus	NN
12235	59	11	,	,	,
12235	59	12	a	a	DT
12235	59	13	low	low	JJ
12235	59	14	total	total	JJ
12235	59	15	word	word	NN
12235	59	16	count	count	NN
12235	59	17	may	may	MD
12235	59	18	impact	impact	VB
12235	59	19	the	the	DT
12235	59	20	degree	degree	NN
12235	59	21	of	of	IN
12235	59	22	Long	long	JJ
12235	59	23	-	-	HYPH
12235	59	24	S	s	NN
12235	59	25	impact	impact	NN
12235	59	26	for	for	IN
12235	59	27	automatic	automatic	JJ
12235	59	28	subject	subject	JJ
12235	59	29	indexing	indexing	NN
12235	59	30	results	result	NNS
12235	59	31	,	,	,
12235	59	32	given	give	VBN
12235	59	33	the	the	DT
12235	59	34	importance	importance	NN
12235	59	35	of	of	IN
12235	59	36	term	term	NN
12235	59	37	availability	availability	NN
12235	59	38	and	and	CC
12235	59	39	frequency	frequency	NN
12235	59	40	for	for	IN
12235	59	41	keyword	keyword	NNP
12235	59	42	extraction	extraction	NNP
12235	59	43	algorithms	algorithm	NNS
12235	59	44	.	.	.
12235	60	1	Figure	figure	NN
12235	60	2	3	3	CD
12235	60	3	.	.	.
12235	61	1	Scatterplot	scatterplot	NN
12235	61	2	of	of	IN
12235	61	3	word	word	NN
12235	61	4	count	count	NN
12235	61	5	for	for	IN
12235	61	6	a	a	DT
12235	61	7	convenience	convenience	NN
12235	61	8	sample	sample	NN
12235	61	9	of	of	IN
12235	61	10	3,849	3,849	CD
12235	61	11	3rd	3rd	NNP
12235	61	12	Edition	Edition	NNP
12235	61	13	Encyclopedia	Encyclopedia	NNP
12235	61	14	Britannica	Britannica	NNP
12235	61	15	entries	entrie	VBZ
12235	61	16	.	.	.
12235	62	1	Large	large	JJ
12235	62	2	-	-	HYPH
12235	62	3	scale	scale	NN
12235	62	4	metadata	metadata	NN
12235	62	5	generation	generation	NN
12235	62	6	requires	require	VBZ
12235	62	7	time	time	NN
12235	62	8	,	,	,
12235	62	9	labor	labor	NN
12235	62	10	,	,	,
12235	62	11	and	and	CC
12235	62	12	resources	resource	NNS
12235	62	13	,	,	,
12235	62	14	and	and	CC
12235	62	15	it	-PRON-	PRP
12235	62	16	becomes	become	VBZ
12235	62	17	more	more	RBR
12235	62	18	costly	costly	JJ
12235	62	19	when	when	WRB
12235	62	20	accounting	account	VBG
12235	62	21	for	for	IN
12235	62	22	the	the	DT
12235	62	23	complications	complication	NNS
12235	62	24	of	of	IN
12235	62	25	correcting	correct	VBG
12235	62	26	the	the	DT
12235	62	27	Long	Long	NNP
12235	62	28	-	-	HYPH
12235	62	29	S	S	NNP
12235	62	30	for	for	IN
12235	62	31	a	a	DT
12235	62	32	particular	particular	JJ
12235	62	33	corpus	corpus	NN
12235	62	34	.	.	.
12235	63	1	Library	library	NN
12235	63	2	and	and	CC
12235	63	3	information	information	NN
12235	63	4	professionals	professional	NNS
12235	63	5	working	work	VBG
12235	63	6	with	with	IN
12235	63	7	digital	digital	JJ
12235	63	8	humanities	humanity	NNS
12235	63	9	resources	resource	NNS
12235	63	10	will	will	MD
12235	63	11	need	need	VB
12235	63	12	to	to	TO
12235	63	13	understand	understand	VB
12235	63	14	the	the	DT
12235	63	15	impact	impact	NN
12235	63	16	of	of	IN
12235	63	17	correcting	correct	VBG
12235	63	18	or	or	CC
12235	63	19	not	not	RB
12235	63	20	corrected	correct	VBN
12235	63	21	the	the	DT
12235	63	22	Long	Long	NNP
12235	63	23	-	-	HYPH
12235	63	24	S	S	NNP
12235	63	25	in	in	IN
12235	63	26	the	the	DT
12235	63	27	corpus	corpus	NN
12235	63	28	before	before	IN
12235	63	29	designating	designate	VBG
12235	63	30	resources	resource	NNS
12235	63	31	and	and	CC
12235	63	32	developing	develop	VBG
12235	63	33	a	a	DT
12235	63	34	protocol	protocol	NN
12235	63	35	for	for	IN
12235	63	36	generating	generate	VBG
12235	63	37	the	the	DT
12235	63	38	automatic	automatic	JJ
12235	63	39	or	or	CC
12235	63	40	semi	semi	JJ
12235	63	41	-	-	JJ
12235	63	42	automatic	automatic	JJ
12235	63	43	metadata	metadata	NN
12235	63	44	for	for	IN
12235	63	45	full	full	JJ
12235	63	46	-	-	HYPH
12235	63	47	text	text	NN
12235	63	48	resources	resource	NNS
12235	63	49	.	.	.
12235	64	1	This	this	DT
12235	64	2	includes	include	VBZ
12235	64	3	understanding	understanding	NN
12235	64	4	whether	whether	IN
12235	64	5	or	or	CC
12235	64	6	not	not	RB
12235	64	7	the	the	DT
12235	64	8	length	length	NN
12235	64	9	of	of	IN
12235	64	10	each	each	DT
12235	64	11	individual	individual	JJ
12235	64	12	document	document	NN
12235	64	13	will	will	MD
12235	64	14	affect	affect	VB
12235	64	15	the	the	DT
12235	64	16	degree	degree	NN
12235	64	17	of	of	IN
12235	64	18	Long	long	JJ
12235	64	19	-	-	HYPH
12235	64	20	S	s	NN
12235	64	21	impact	impact	NN
12235	64	22	upon	upon	IN
12235	64	23	the	the	DT
12235	64	24	results	result	NNS
12235	64	25	.	.	.
12235	65	1	This	this	DT
12235	65	2	challenge	challenge	NN
12235	65	3	,	,	,
12235	65	4	and	and	CC
12235	65	5	issues	issue	NNS
12235	65	6	reviewed	review	VBN
12235	65	7	above	above	RB
12235	65	8	,	,	,
12235	65	9	are	be	VBP
12235	65	10	in	in	IN
12235	65	11	the	the	DT
12235	65	12	research	research	NN
12235	65	13	presented	present	VBN
12235	65	14	below	below	RB
12235	65	15	.	.	.
12235	66	1	OBJECTIVES	OBJECTIVES	NNP
12235	66	2	The	the	DT
12235	66	3	overriding	override	VBG
12235	66	4	goal	goal	NN
12235	66	5	of	of	IN
12235	66	6	this	this	DT
12235	66	7	work	work	NN
12235	66	8	is	be	VBZ
12235	66	9	to	to	TO
12235	66	10	determine	determine	VB
12235	66	11	the	the	DT
12235	66	12	prevalence	prevalence	NN
12235	66	13	of	of	IN
12235	66	14	omitted	omit	VBN
12235	66	15	terms	term	NNS
12235	66	16	in	in	IN
12235	66	17	automatic	automatic	JJ
12235	66	18	subject	subject	JJ
12235	66	19	indexing	indexing	NN
12235	66	20	results	result	NNS
12235	66	21	when	when	WRB
12235	66	22	the	the	DT
12235	66	23	Long	Long	NNP
12235	66	24	-	-	HYPH
12235	66	25	S	S	NNP
12235	66	26	is	be	VBZ
12235	66	27	not	not	RB
12235	66	28	corrected	correct	VBN
12235	66	29	in	in	IN
12235	66	30	the	the	DT
12235	66	31	3rd	3rd	JJ
12235	66	32	edition	edition	NN
12235	66	33	entries	entry	NNS
12235	66	34	of	of	IN
12235	66	35	the	the	DT
12235	66	36	Encyclopedia	Encyclopedia	NNP
12235	66	37	Britannica	Britannica	NNP
12235	66	38	.	.	.
12235	67	1	Research	research	NN
12235	67	2	questions	question	NNS
12235	67	3	:	:	:
12235	67	4	1	1	LS
12235	67	5	.	.	.
12235	68	1	What	what	WP
12235	68	2	is	be	VBZ
12235	68	3	the	the	DT
12235	68	4	average	average	JJ
12235	68	5	number	number	NN
12235	68	6	of	of	IN
12235	68	7	terms	term	NNS
12235	68	8	that	that	WDT
12235	68	9	are	be	VBP
12235	68	10	omitted	omit	VBN
12235	68	11	from	from	IN
12235	68	12	automatic	automatic	JJ
12235	68	13	subject	subject	JJ
12235	68	14	indexing	indexing	NN
12235	68	15	results	result	NNS
12235	68	16	when	when	WRB
12235	68	17	the	the	DT
12235	68	18	Long	Long	NNP
12235	68	19	-	-	HYPH
12235	68	20	S	S	NNP
12235	68	21	is	be	VBZ
12235	68	22	not	not	RB
12235	68	23	corrected	correct	VBN
12235	68	24	to	to	IN
12235	68	25	a	a	DT
12235	68	26	standard	standard	NN
12235	68	27	<	<	XX
12235	68	28	s	s	XX
12235	68	29	>	>	XX
12235	68	30	?	?	.
12235	69	1	2	2	LS
12235	69	2	.	.	.
12235	70	1	How	how	WRB
12235	70	2	does	do	VBZ
12235	70	3	the	the	DT
12235	70	4	encyclopedia	encyclopedia	NN
12235	70	5	entry	entry	NN
12235	70	6	length	length	NN
12235	70	7	affect	affect	VBP
12235	70	8	the	the	DT
12235	70	9	number	number	NN
12235	70	10	of	of	IN
12235	70	11	terms	term	NNS
12235	70	12	that	that	WDT
12235	70	13	are	be	VBP
12235	70	14	omitted	omit	VBN
12235	70	15	when	when	WRB
12235	70	16	the	the	DT
12235	70	17	Long	Long	NNP
12235	70	18	-	-	HYPH
12235	70	19	S	S	NNP
12235	70	20	is	be	VBZ
12235	70	21	not	not	RB
12235	70	22	corrected	correct	VBN
12235	70	23	to	to	IN
12235	70	24	a	a	DT
12235	70	25	standard	standard	NN
12235	70	26	<	<	XX
12235	70	27	s	s	XX
12235	70	28	>	>	XX
12235	70	29	?	?	.
12235	71	1	This	this	DT
12235	71	2	analysis	analysis	NN
12235	71	3	will	will	MD
12235	71	4	approach	approach	VB
12235	71	5	these	these	DT
12235	71	6	goals	goal	NNS
12235	71	7	by	by	IN
12235	71	8	performing	perform	VBG
12235	71	9	a	a	DT
12235	71	10	comparative	comparative	JJ
12235	71	11	analysis	analysis	NN
12235	71	12	of	of	IN
12235	71	13	automatic	automatic	JJ
12235	71	14	subject	subject	JJ
12235	71	15	indexing	indexing	NN
12235	71	16	results	result	NNS
12235	71	17	to	to	TO
12235	71	18	determine	determine	VB
12235	71	19	the	the	DT
12235	71	20	number	number	NN
12235	71	21	of	of	IN
12235	71	22	terms	term	NNS
12235	71	23	that	that	WDT
12235	71	24	are	be	VBP
12235	71	25	omitted	omit	VBN
12235	71	26	from	from	IN
12235	71	27	the	the	DT
12235	71	28	results	result	NNS
12235	71	29	when	when	WRB
12235	71	30	the	the	DT
12235	71	31	Long	Long	NNP
12235	71	32	-	-	HYPH
12235	71	33	S	S	NNP
12235	71	34	is	be	VBZ
12235	71	35	not	not	RB
12235	71	36	corrected	correct	VBN
12235	71	37	to	to	IN
12235	71	38	a	a	DT
12235	71	39	standard	standard	JJ
12235	71	40	letter	letter	NN
12235	71	41	<	<	XX
12235	71	42	s	s	NNP
12235	71	43	>	>	XX
12235	71	44	.	.	.
12235	72	1	Basic	basic	JJ
12235	72	2	descriptive	descriptive	JJ
12235	72	3	statistics	statistic	NNS
12235	72	4	are	be	VBP
12235	72	5	generated	generate	VBN
12235	72	6	to	to	TO
12235	72	7	determine	determine	VB
12235	72	8	central	central	JJ
12235	72	9	tendency	tendency	NN
12235	72	10	.	.	.
12235	73	1	The	the	DT
12235	73	2	quantity	quantity	NN
12235	73	3	of	of	IN
12235	73	4	terms	term	NNS
12235	73	5	omitted	omit	VBN
12235	73	6	are	be	VBP
12235	73	7	then	then	RB
12235	73	8	compared	compare	VBN
12235	73	9	with	with	IN
12235	73	10	encyclopedia	encyclopedia	JJ
12235	73	11	INFORMATION	INFORMATION	NNP
12235	73	12	TECHNOLOGY	technology	NN
12235	73	13	AND	and	CC
12235	73	14	LIBRARIES	library	NNS
12235	73	15	SEPTEMBER	SEPTEMBER	NNP
12235	73	16	2020	2020	CD
12235	73	17	EVALUATING	evaluate	VBG
12235	73	18	THE	the	DT
12235	73	19	IMPACT	impact	NN
12235	73	20	OF	of	IN
12235	73	21	THE	the	DT
12235	73	22	LONG	long	JJ
12235	73	23	-	-	HYPH
12235	73	24	S	S	NNP
12235	73	25	|	|	NNP
12235	73	26	GRABUS	grabus	NN
12235	73	27	6	6	CD
12235	73	28	entry	entry	NN
12235	73	29	word	word	NN
12235	73	30	counts	count	NNS
12235	73	31	.	.	.
12235	74	1	These	these	DT
12235	74	2	objectives	objective	NNS
12235	74	3	were	be	VBD
12235	74	4	shaped	shape	VBN
12235	74	5	by	by	IN
12235	74	6	collaboration	collaboration	NN
12235	74	7	between	between	IN
12235	74	8	Drexel	Drexel	NNP
12235	74	9	University	University	NNP
12235	74	10	’s	’s	POS
12235	74	11	Metadata	Metadata	NNP
12235	74	12	Research	Research	NNP
12235	74	13	Center	Center	NNP
12235	74	14	and	and	CC
12235	74	15	Temple	Temple	NNP
12235	74	16	University	University	NNP
12235	74	17	’s	’s	POS
12235	74	18	Digital	Digital	NNP
12235	74	19	Scholarship	Scholarship	NNP
12235	74	20	Center	Center	NNP
12235	74	21	.	.	.
12235	75	1	The	the	DT
12235	75	2	next	next	JJ
12235	75	3	section	section	NN
12235	75	4	of	of	IN
12235	75	5	this	this	DT
12235	75	6	paper	paper	NN
12235	75	7	will	will	MD
12235	75	8	report	report	VB
12235	75	9	on	on	IN
12235	75	10	methods	method	NNS
12235	75	11	and	and	CC
12235	75	12	steps	step	NNS
12235	75	13	taken	take	VBN
12235	75	14	to	to	TO
12235	75	15	address	address	VB
12235	75	16	these	these	DT
12235	75	17	objectives	objective	NNS
12235	75	18	.	.	.
12235	76	1	METHODS	METHODS	NNP
12235	76	2	We	-PRON-	PRP
12235	76	3	approached	approach	VBD
12235	76	4	this	this	DT
12235	76	5	research	research	NN
12235	76	6	by	by	IN
12235	76	7	performing	perform	VBG
12235	76	8	a	a	DT
12235	76	9	comparative	comparative	JJ
12235	76	10	analysis	analysis	NN
12235	76	11	of	of	IN
12235	76	12	subject	subject	JJ
12235	76	13	metadata	metadata	NN
12235	76	14	generated	generate	VBD
12235	76	15	both	both	CC
12235	76	16	before	before	IN
12235	76	17	and	and	CC
12235	76	18	after	after	IN
12235	76	19	the	the	DT
12235	76	20	correction	correction	NN
12235	76	21	of	of	IN
12235	76	22	the	the	DT
12235	76	23	historical	historical	JJ
12235	76	24	Long	Long	NNP
12235	76	25	-	-	HYPH
12235	76	26	S	S	NNP
12235	76	27	in	in	IN
12235	76	28	the	the	DT
12235	76	29	3rd	3rd	JJ
12235	76	30	edition	edition	NN
12235	76	31	of	of	IN
12235	76	32	the	the	DT
12235	76	33	Encyclopedia	Encyclopedia	NNP
12235	76	34	Britannica	Britannica	NNP
12235	76	35	.	.	.
12235	77	1	The	the	DT
12235	77	2	HIVE	HIVE	NNP
12235	77	3	tool	tool	NN
12235	77	4	was	be	VBD
12235	77	5	used	use	VBN
12235	77	6	to	to	TO
12235	77	7	automatically	automatically	RB
12235	77	8	generate	generate	VB
12235	77	9	the	the	DT
12235	77	10	subject	subject	JJ
12235	77	11	metadata	metadata	NN
12235	77	12	.	.	.
12235	78	1	Descriptive	descriptive	JJ
12235	78	2	statistics	statistic	NNS
12235	78	3	were	be	VBD
12235	78	4	applied	apply	VBN
12235	78	5	,	,	,
12235	78	6	and	and	CC
12235	78	7	visualizations	visualization	NNS
12235	78	8	produced	produce	VBN
12235	78	9	from	from	IN
12235	78	10	the	the	DT
12235	78	11	results	result	NNS
12235	78	12	were	be	VBD
12235	78	13	also	also	RB
12235	78	14	examined	examine	VBN
12235	78	15	to	to	TO
12235	78	16	identify	identify	VB
12235	78	17	trends	trend	NNS
12235	78	18	.	.	.
12235	79	1	Figure	figure	NN
12235	79	2	4	4	CD
12235	79	3	.	.	.
12235	80	1	The	the	DT
12235	80	2	30	30	CD
12235	80	3	Encyclopedia	Encyclopedia	NNP
12235	80	4	Britannica	Britannica	NNP
12235	80	5	3rd	3rd	JJ
12235	80	6	edition	edition	NN
12235	80	7	Encyclopedia	Encyclopedia	NNP
12235	80	8	Britannica	Britannica	NNP
12235	80	9	entries	entry	NNS
12235	80	10	randomly	randomly	RB
12235	80	11	selected	select	VBN
12235	80	12	for	for	IN
12235	80	13	this	this	DT
12235	80	14	study	study	NN
12235	80	15	,	,	,
12235	80	16	sorted	sort	VBN
12235	80	17	in	in	IN
12235	80	18	ascending	ascend	VBG
12235	80	19	order	order	NN
12235	80	20	by	by	IN
12235	80	21	their	-PRON-	PRP$
12235	80	22	word	word	NN
12235	80	23	counts	count	NNS
12235	80	24	.	.	.
12235	81	1	The	the	DT
12235	81	2	protocol	protocol	NN
12235	81	3	for	for	IN
12235	81	4	performing	perform	VBG
12235	81	5	this	this	DT
12235	81	6	research	research	NN
12235	81	7	involved	involve	VBD
12235	81	8	the	the	DT
12235	81	9	following	following	JJ
12235	81	10	steps	step	NNS
12235	81	11	:	:	:
12235	81	12	1	1	CD
12235	81	13	.	.	.
12235	82	1	Compile	compile	VB
12235	82	2	a	a	DT
12235	82	3	sample	sample	NN
12235	82	4	for	for	IN
12235	82	5	testing	testing	NN
12235	82	6	:	:	:
12235	82	7	1.1	1.1	CD
12235	82	8	.	.	.
12235	83	1	A	a	DT
12235	83	2	random	random	JJ
12235	83	3	sample	sample	NN
12235	83	4	of	of	IN
12235	83	5	30	30	CD
12235	83	6	encyclopedia	encyclopedia	NN
12235	83	7	entries	entry	NNS
12235	83	8	was	be	VBD
12235	83	9	identified	identify	VBN
12235	83	10	from	from	IN
12235	83	11	a	a	DT
12235	83	12	convenience	convenience	NN
12235	83	13	sample	sample	NN
12235	83	14	of	of	IN
12235	83	15	entries	entry	NNS
12235	83	16	that	that	WDT
12235	83	17	comprise	comprise	VBP
12235	83	18	the	the	DT
12235	83	19	letter	letter	NN
12235	83	20	S	S	NNP
12235	83	21	volumes	volume	NNS
12235	83	22	of	of	IN
12235	83	23	the	the	DT
12235	83	24	3rd	3rd	JJ
12235	83	25	edition	edition	NN
12235	83	26	.	.	.
12235	84	1	The	the	DT
12235	84	2	entries	entry	NNS
12235	84	3	range	range	VBP
12235	84	4	,	,	,
12235	84	5	in	in	IN
12235	84	6	length	length	NN
12235	84	7	,	,	,
12235	84	8	from	from	IN
12235	84	9	6	6	CD
12235	84	10	to	to	IN
12235	84	11	6,114	6,114	CD
12235	84	12	words	word	NNS
12235	84	13	.	.	.
12235	85	1	The	the	DT
12235	85	2	median	median	JJ
12235	85	3	word	word	NN
12235	85	4	count	count	NN
12235	85	5	for	for	IN
12235	85	6	entries	entry	NNS
12235	85	7	in	in	IN
12235	85	8	this	this	DT
12235	85	9	sample	sample	NN
12235	85	10	is	be	VBZ
12235	85	11	99	99	CD
12235	85	12	words	word	NNS
12235	85	13	.	.	.
12235	86	1	1.2	1.2	CD
12235	86	2	.	.	.
12235	87	1	The	the	DT
12235	87	2	sample	sample	NN
12235	87	3	of	of	IN
12235	87	4	terms	term	NNS
12235	87	5	selected	select	VBN
12235	87	6	for	for	IN
12235	87	7	this	this	DT
12235	87	8	study	study	NN
12235	87	9	and	and	CC
12235	87	10	their	-PRON-	PRP$
12235	87	11	respective	respective	JJ
12235	87	12	word	word	NN
12235	87	13	counts	count	NNS
12235	87	14	are	be	VBP
12235	87	15	visualized	visualize	VBN
12235	87	16	in	in	IN
12235	87	17	figure	figure	NN
12235	87	18	4	4	CD
12235	87	19	.	.	.
12235	88	1	1.3	1.3	CD
12235	88	2	.	.	.
12235	89	1	For	for	IN
12235	89	2	each	each	DT
12235	89	3	entry	entry	NN
12235	89	4	,	,	,
12235	89	5	the	the	DT
12235	89	6	Long	long	JJ
12235	89	7	-	-	HYPH
12235	89	8	S	S	NNP
12235	89	9	terms	term	NNS
12235	89	10	in	in	IN
12235	89	11	the	the	DT
12235	89	12	original	original	JJ
12235	89	13	XML	xml	NN
12235	89	14	file	file	NN
12235	89	15	were	be	VBD
12235	89	16	extracted	extract	VBN
12235	89	17	to	to	IN
12235	89	18	a	a	DT
12235	89	19	list	list	NN
12235	89	20	.	.	.
12235	90	1	2	2	LS
12235	90	2	.	.	.
12235	91	1	Perform	perform	VB
12235	91	2	automatic	automatic	JJ
12235	91	3	subject	subject	JJ
12235	91	4	indexing	indexing	NN
12235	91	5	sequence	sequence	NN
12235	91	6	upon	upon	IN
12235	91	7	entries	entry	NNS
12235	91	8	to	to	TO
12235	91	9	generate	generate	VB
12235	91	10	lists	list	NNS
12235	91	11	of	of	IN
12235	91	12	terms	term	NNS
12235	91	13	:	:	:
12235	91	14	2.1	2.1	CD
12235	91	15	.	.	.
12235	92	1	Using	use	VBG
12235	92	2	the	the	DT
12235	92	3	2018	2018	CD
12235	92	4	and	and	CC
12235	92	5	1910	1910	CD
12235	92	6	versions	version	NNS
12235	92	7	of	of	IN
12235	92	8	the	the	DT
12235	92	9	LCSH	LCSH	NNP
12235	92	10	.	.	.
12235	93	1	2.2	2.2	CD
12235	93	2	.	.	.
12235	94	1	With	with	IN
12235	94	2	fixed	fix	VBN
12235	94	3	maximum	maximum	JJ
12235	94	4	subject	subject	JJ
12235	94	5	heading	heading	NN
12235	94	6	results	result	NNS
12235	94	7	set	set	VBN
12235	94	8	to	to	IN
12235	94	9	40	40	CD
12235	94	10	:	:	:
12235	94	11	20	20	CD
12235	94	12	maximum	maximum	JJ
12235	94	13	terms	term	NNS
12235	94	14	returned	return	VBD
12235	94	15	with	with	IN
12235	94	16	the	the	DT
12235	94	17	2018	2018	CD
12235	94	18	LCSH	LCSH	NNP
12235	94	19	,	,	,
12235	94	20	and	and	CC
12235	94	21	20	20	CD
12235	94	22	maximum	maximum	JJ
12235	94	23	terms	term	NNS
12235	94	24	returned	return	VBD
12235	94	25	with	with	IN
12235	94	26	the	the	DT
12235	94	27	1910	1910	CD
12235	94	28	LCSH	LCSH	NNP
12235	94	29	.	.	.
12235	95	1	2.3	2.3	LS
12235	95	2	.	.	.
12235	96	1	Before	before	IN
12235	96	2	Long	Long	NNP
12235	96	3	-	-	HYPH
12235	96	4	S	S	NNP
12235	96	5	correction	correction	NN
12235	96	6	and	and	CC
12235	96	7	after	after	IN
12235	96	8	Long	Long	NNP
12235	96	9	-	-	HYPH
12235	96	10	S	S	NNP
12235	96	11	correction	correction	NN
12235	96	12	,	,	,
12235	96	13	using	use	VBG
12235	96	14	the	the	DT
12235	96	15	Oxygen	Oxygen	NNP
12235	96	16	XML	XML	NNP
12235	96	17	Editor	Editor	NNP
12235	96	18	TEI	TEI	NNP
12235	96	19	to	to	IN
12235	96	20	TXT	TXT	NNP
12235	96	21	transformation	transformation	NN
12235	96	22	.	.	.
12235	97	1	INFORMATION	INFORMATION	NNP
12235	97	2	TECHNOLOGY	technology	NN
12235	97	3	AND	and	CC
12235	97	4	LIBRARIES	library	NNS
12235	97	5	SEPTEMBER	SEPTEMBER	NNP
12235	97	6	2020	2020	CD
12235	97	7	EVALUATING	evaluate	VBG
12235	97	8	THE	the	DT
12235	97	9	IMPACT	impact	NN
12235	97	10	OF	of	IN
12235	97	11	THE	the	DT
12235	97	12	LONG	long	JJ
12235	97	13	-	-	HYPH
12235	97	14	S	S	NNP
12235	97	15	|	|	NNP
12235	97	16	GRABUS	grabus	NN
12235	97	17	7	7	CD
12235	97	18	3	3	CD
12235	97	19	.	.	.
12235	98	1	Perform	perform	VB
12235	98	2	outer	outer	JJ
12235	98	3	join	join	VBP
12235	98	4	on	on	IN
12235	98	5	Python	Python	NNP
12235	98	6	Data	Data	NNP
12235	98	7	Frames	Frames	NNPS
12235	98	8	,	,	,
12235	98	9	between	between	IN
12235	98	10	terms	term	NNS
12235	98	11	generated	generate	VBN
12235	98	12	when	when	WRB
12235	98	13	the	the	DT
12235	98	14	Long	Long	NNP
12235	98	15	-	-	HYPH
12235	98	16	S	S	NNP
12235	98	17	has	have	VBZ
12235	98	18	been	be	VBN
12235	98	19	corrected	correct	VBN
12235	98	20	vs.	vs.	IN
12235	98	21	terms	term	NNS
12235	98	22	generated	generate	VBN
12235	98	23	when	when	WRB
12235	98	24	the	the	DT
12235	98	25	Long	Long	NNP
12235	98	26	-	-	HYPH
12235	98	27	S	S	NNP
12235	98	28	has	have	VBZ
12235	98	29	not	not	RB
12235	98	30	been	be	VBN
12235	98	31	corrected	correct	VBN
12235	98	32	.	.	.
12235	99	1	The	the	DT
12235	99	2	resulting	result	VBG
12235	99	3	left	left	JJ
12235	99	4	outer	outer	JJ
12235	99	5	join	join	NN
12235	99	6	list	list	NN
12235	99	7	displays	display	VBZ
12235	99	8	terms	term	NNS
12235	99	9	that	that	WDT
12235	99	10	are	be	VBP
12235	99	11	omitted	omit	VBN
12235	99	12	from	from	IN
12235	99	13	the	the	DT
12235	99	14	automatic	automatic	JJ
12235	99	15	indexing	indexing	NN
12235	99	16	results	result	NNS
12235	99	17	if	if	IN
12235	99	18	the	the	DT
12235	99	19	Long	Long	NNP
12235	99	20	-	-	HYPH
12235	99	21	S	S	NNP
12235	99	22	is	be	VBZ
12235	99	23	not	not	RB
12235	99	24	corrected	correct	VBN
12235	99	25	to	to	IN
12235	99	26	a	a	DT
12235	99	27	standard	standard	JJ
12235	99	28	small	small	JJ
12235	99	29	<	<	XX
12235	99	30	s	s	NNP
12235	99	31	>	>	XX
12235	99	32	.	.	.
12235	100	1	The	the	DT
12235	100	2	quantity	quantity	NN
12235	100	3	of	of	IN
12235	100	4	terms	term	NNS
12235	100	5	omitted	omit	VBN
12235	100	6	are	be	VBP
12235	100	7	recorded	record	VBN
12235	100	8	for	for	IN
12235	100	9	comparison	comparison	NN
12235	100	10	.	.	.
12235	101	1	4	4	LS
12235	101	2	.	.	.
12235	102	1	Analysis	analysis	NN
12235	102	2	:	:	:
12235	102	3	Descriptive	descriptive	JJ
12235	102	4	statistics	statistic	NNS
12235	102	5	were	be	VBD
12235	102	6	generated	generate	VBN
12235	102	7	to	to	TO
12235	102	8	determine	determine	VB
12235	102	9	central	central	JJ
12235	102	10	tendency	tendency	NN
12235	102	11	for	for	IN
12235	102	12	the	the	DT
12235	102	13	number	number	NN
12235	102	14	and	and	CC
12235	102	15	percentage	percentage	NN
12235	102	16	of	of	IN
12235	102	17	words	word	NNS
12235	102	18	omitted	omit	VBN
12235	102	19	when	when	WRB
12235	102	20	the	the	DT
12235	102	21	Long	Long	NNP
12235	102	22	-	-	HYPH
12235	102	23	S	S	NNP
12235	102	24	is	be	VBZ
12235	102	25	not	not	RB
12235	102	26	corrected	correct	VBN
12235	102	27	.	.	.
12235	103	1	The	the	DT
12235	103	2	quantity	quantity	NN
12235	103	3	of	of	IN
12235	103	4	terms	term	NNS
12235	103	5	omitted	omit	VBN
12235	103	6	are	be	VBP
12235	103	7	also	also	RB
12235	103	8	visualized	visualize	VBN
12235	103	9	in	in	IN
12235	103	10	a	a	DT
12235	103	11	continuous	continuous	JJ
12235	103	12	scatterplot	scatterplot	NN
12235	103	13	with	with	IN
12235	103	14	the	the	DT
12235	103	15	corresponding	correspond	VBG
12235	103	16	word	word	NN
12235	103	17	counts	count	NNS
12235	103	18	,	,	,
12235	103	19	to	to	TO
12235	103	20	demonstrate	demonstrate	VB
12235	103	21	that	that	IN
12235	103	22	the	the	DT
12235	103	23	quantity	quantity	NN
12235	103	24	of	of	IN
12235	103	25	terms	term	NNS
12235	103	26	omitted	omit	VBN
12235	103	27	when	when	WRB
12235	103	28	the	the	DT
12235	103	29	Long	Long	NNP
12235	103	30	-	-	HYPH
12235	103	31	S	S	NNP
12235	103	32	is	be	VBZ
12235	103	33	not	not	RB
12235	103	34	corrected	correct	VBN
12235	103	35	seems	seem	VBZ
12235	103	36	to	to	TO
12235	103	37	relate	relate	VB
12235	103	38	to	to	IN
12235	103	39	the	the	DT
12235	103	40	length	length	NN
12235	103	41	of	of	IN
12235	103	42	the	the	DT
12235	103	43	document	document	NN
12235	103	44	being	be	VBG
12235	103	45	automatically	automatically	RB
12235	103	46	classified	classify	VBN
12235	103	47	.	.	.
12235	104	1	RESULTS	RESULTS	NNP
12235	104	2	The	the	DT
12235	104	3	results	result	NNS
12235	104	4	report	report	VBP
12235	104	5	the	the	DT
12235	104	6	prevalence	prevalence	NN
12235	104	7	of	of	IN
12235	104	8	omitted	omitted	JJ
12235	104	9	terms	term	NNS
12235	104	10	when	when	WRB
12235	104	11	the	the	DT
12235	104	12	Long	Long	NNP
12235	104	13	-	-	HYPH
12235	104	14	S	S	NNP
12235	104	15	is	be	VBZ
12235	104	16	not	not	RB
12235	104	17	corrected	correct	VBN
12235	104	18	to	to	IN
12235	104	19	a	a	DT
12235	104	20	standard	standard	NN
12235	104	21	<	<	XX
12235	104	22	s	s	NNP
12235	104	23	>	>	XX
12235	104	24	,	,	,
12235	104	25	as	as	RB
12235	104	26	well	well	RB
12235	104	27	as	as	IN
12235	104	28	a	a	DT
12235	104	29	visualization	visualization	NN
12235	104	30	of	of	IN
12235	104	31	the	the	DT
12235	104	32	number	number	NN
12235	104	33	of	of	IN
12235	104	34	terms	term	NNS
12235	104	35	omitted	omit	VBN
12235	104	36	as	as	IN
12235	104	37	they	-PRON-	PRP
12235	104	38	relate	relate	VBP
12235	104	39	to	to	IN
12235	104	40	the	the	DT
12235	104	41	encyclopedia	encyclopedia	NNS
12235	104	42	entry	entry	NN
12235	104	43	length	length	NN
12235	104	44	.	.	.
12235	105	1	For	for	IN
12235	105	2	each	each	DT
12235	105	3	of	of	IN
12235	105	4	the	the	DT
12235	105	5	30	30	CD
12235	105	6	sample	sample	NN
12235	105	7	entries	entry	NNS
12235	105	8	automatically	automatically	RB
12235	105	9	indexed	index	VBN
12235	105	10	with	with	IN
12235	105	11	HIVE	HIVE	NNP
12235	105	12	,	,	,
12235	105	13	a	a	DT
12235	105	14	fixed	fix	VBN
12235	105	15	maximum	maximum	JJ
12235	105	16	number	number	NN
12235	105	17	of	of	IN
12235	105	18	40	40	CD
12235	105	19	entries	entry	NNS
12235	105	20	were	be	VBD
12235	105	21	returned	return	VBN
12235	105	22	:	:	:
12235	105	23	a	a	DT
12235	105	24	maximum	maximum	NN
12235	105	25	of	of	IN
12235	105	26	20	20	CD
12235	105	27	terms	term	NNS
12235	105	28	using	use	VBG
12235	105	29	the	the	DT
12235	105	30	2018	2018	CD
12235	105	31	LCSH	LCSH	NNP
12235	105	32	,	,	,
12235	105	33	and	and	CC
12235	105	34	a	a	DT
12235	105	35	maximum	maximum	NN
12235	105	36	of	of	IN
12235	105	37	20	20	CD
12235	105	38	terms	term	NNS
12235	105	39	using	use	VBG
12235	105	40	the	the	DT
12235	105	41	1910	1910	CD
12235	105	42	LCSH	LCSH	NNP
12235	105	43	.	.	.
12235	106	1	As	as	IN
12235	106	2	seen	see	VBN
12235	106	3	in	in	IN
12235	106	4	table	table	NN
12235	106	5	1	1	CD
12235	106	6	,	,	,
12235	106	7	central	central	JJ
12235	106	8	tendency	tendency	NN
12235	106	9	is	be	VBZ
12235	106	10	measured	measure	VBN
12235	106	11	using	use	VBG
12235	106	12	the	the	DT
12235	106	13	arithmetic	arithmetic	JJ
12235	106	14	mean	mean	NNP
12235	106	15	and	and	CC
12235	106	16	median	median	NNP
12235	106	17	,	,	,
12235	106	18	along	along	IN
12235	106	19	with	with	IN
12235	106	20	the	the	DT
12235	106	21	standard	standard	JJ
12235	106	22	deviation	deviation	NN
12235	106	23	and	and	CC
12235	106	24	range	range	NN
12235	106	25	.	.	.
12235	107	1	The	the	DT
12235	107	2	average	average	JJ
12235	107	3	number	number	NN
12235	107	4	of	of	IN
12235	107	5	terms	term	NNS
12235	107	6	omitted	omit	VBN
12235	107	7	from	from	IN
12235	107	8	an	an	DT
12235	107	9	entry	entry	NN
12235	107	10	’s	’s	POS
12235	107	11	results	result	NNS
12235	107	12	is	be	VBZ
12235	107	13	6.73	6.73	CD
12235	107	14	,	,	,
12235	107	15	and	and	CC
12235	107	16	the	the	DT
12235	107	17	average	average	JJ
12235	107	18	percentage	percentage	NN
12235	107	19	of	of	IN
12235	107	20	terms	term	NNS
12235	107	21	omitted	omit	VBN
12235	107	22	from	from	IN
12235	107	23	an	an	DT
12235	107	24	entry	entry	NN
12235	107	25	’s	’s	POS
12235	107	26	results	result	NNS
12235	107	27	is	be	VBZ
12235	107	28	26.51	26.51	CD
12235	107	29	percent	percent	NN
12235	107	30	,	,	,
12235	107	31	with	with	IN
12235	107	32	the	the	DT
12235	107	33	2018	2018	CD
12235	107	34	and	and	CC
12235	107	35	1910	1910	CD
12235	107	36	editions	edition	NNS
12235	107	37	of	of	IN
12235	107	38	LCSH	LCSH	NNP
12235	107	39	performing	perform	VBG
12235	107	40	at	at	IN
12235	107	41	similar	similar	JJ
12235	107	42	rates	rate	NNS
12235	107	43	.	.	.
12235	108	1	The	the	DT
12235	108	2	full	full	JJ
12235	108	3	results	result	NNS
12235	108	4	are	be	VBP
12235	108	5	displayed	display	VBN
12235	108	6	in	in	IN
12235	108	7	appendix	appendix	NNP
12235	108	8	A.	A.	NNP
12235	109	1	Table	table	NN
12235	109	2	1	1	CD
12235	109	3	.	.	.
12235	110	1	Measures	measure	NNS
12235	110	2	of	of	IN
12235	110	3	centrality	centrality	NN
12235	110	4	,	,	,
12235	110	5	standard	standard	JJ
12235	110	6	deviation	deviation	NN
12235	110	7	,	,	,
12235	110	8	range	range	NN
12235	110	9	,	,	,
12235	110	10	and	and	CC
12235	110	11	percentage	percentage	NN
12235	110	12	for	for	IN
12235	110	13	quantity	quantity	NN
12235	110	14	of	of	IN
12235	110	15	terms	term	NNS
12235	110	16	omitted	omit	VBN
12235	110	17	when	when	WRB
12235	110	18	the	the	DT
12235	110	19	Long	Long	NNP
12235	110	20	-	-	HYPH
12235	110	21	S	S	NNP
12235	110	22	is	be	VBZ
12235	110	23	not	not	RB
12235	110	24	corrected	correct	VBN
12235	110	25	to	to	IN
12235	110	26	a	a	DT
12235	110	27	standard	standard	NN
12235	110	28	<	<	XX
12235	110	29	s	s	NNP
12235	110	30	>	>	XX
12235	110	31	,	,	,
12235	110	32	rounded	round	VBD
12235	110	33	to	to	IN
12235	110	34	the	the	DT
12235	110	35	hundredth	hundredth	JJ
12235	110	36	.	.	.
12235	111	1	For	for	IN
12235	111	2	each	each	DT
12235	111	3	entry	entry	NN
12235	111	4	,	,	,
12235	111	5	a	a	DT
12235	111	6	maximum	maximum	NN
12235	111	7	of	of	IN
12235	111	8	40	40	CD
12235	111	9	terms	term	NNS
12235	111	10	were	be	VBD
12235	111	11	returned	return	VBN
12235	111	12	:	:	:
12235	111	13	20	20	CD
12235	111	14	using	use	VBG
12235	111	15	2018	2018	CD
12235	111	16	LCSH	LCSH	NNP
12235	111	17	and	and	CC
12235	111	18	20	20	CD
12235	111	19	using	use	VBG
12235	111	20	1910	1910	CD
12235	111	21	LCSH	LCSH	NNP
12235	111	22	.	.	.
12235	112	1	The	the	DT
12235	112	2	total	total	JJ
12235	112	3	results	result	NNS
12235	112	4	returned	return	VBD
12235	112	5	varies	varie	NNS
12235	112	6	according	accord	VBG
12235	112	7	to	to	IN
12235	112	8	the	the	DT
12235	112	9	entry	entry	NN
12235	112	10	length	length	NN
12235	112	11	.	.	.
12235	113	1	These	these	DT
12235	113	2	totals	total	NNS
12235	113	3	are	be	VBP
12235	113	4	reported	report	VBN
12235	113	5	in	in	IN
12235	113	6	appendix	appendix	NNP
12235	113	7	B.	B.	NNP
12235	114	1	(	(	-LRB-
12235	114	2	N=	N=	NNP
12235	114	3	30	30	CD
12235	114	4	entries	entry	NNS
12235	114	5	.	.	.
12235	114	6	)	)	-RRB-
12235	115	1	For	for	IN
12235	115	2	each	each	DT
12235	115	3	entry	entry	NN
12235	115	4	in	in	IN
12235	115	5	the	the	DT
12235	115	6	sample	sample	NN
12235	115	7	,	,	,
12235	115	8	the	the	DT
12235	115	9	results	result	NNS
12235	115	10	in	in	IN
12235	115	11	appendix	appendix	NNP
12235	115	12	A	a	DT
12235	115	13	display	display	NN
12235	115	14	the	the	DT
12235	115	15	total	total	JJ
12235	115	16	words	word	NNS
12235	115	17	omitted	omit	VBN
12235	115	18	when	when	WRB
12235	115	19	the	the	DT
12235	115	20	Long	Long	NNP
12235	115	21	-	-	HYPH
12235	115	22	S	S	NNP
12235	115	23	is	be	VBZ
12235	115	24	not	not	RB
12235	115	25	corrected	correct	VBN
12235	115	26	,	,	,
12235	115	27	the	the	DT
12235	115	28	number	number	NN
12235	115	29	of	of	IN
12235	115	30	2018	2018	CD
12235	115	31	LCSH	LCSH	NNP
12235	115	32	terms	term	NNS
12235	115	33	omitted	omit	VBN
12235	115	34	,	,	,
12235	115	35	the	the	DT
12235	115	36	number	number	NN
12235	115	37	of	of	IN
12235	115	38	1910	1910	CD
12235	115	39	LCSH	LCSH	NNP
12235	115	40	terms	term	NNS
12235	115	41	omitted	omit	VBD
12235	115	42	,	,	,
12235	115	43	and	and	CC
12235	115	44	the	the	DT
12235	115	45	encyclopedia	encyclopedia	NNS
12235	115	46	entry	entry	NN
12235	115	47	word	word	NN
12235	115	48	count	count	NN
12235	115	49	.	.	.
12235	116	1	Figure	figure	NN
12235	116	2	5	5	CD
12235	116	3	visualizes	visualize	VBZ
12235	116	4	the	the	DT
12235	116	5	total	total	JJ
12235	116	6	number	number	NN
12235	116	7	of	of	IN
12235	116	8	terms	term	NNS
12235	116	9	omitted	omit	VBN
12235	116	10	for	for	IN
12235	116	11	each	each	DT
12235	116	12	entry	entry	NN
12235	116	13	when	when	WRB
12235	116	14	the	the	DT
12235	116	15	Long	Long	NNP
12235	116	16	-	-	HYPH
12235	116	17	S	S	NNP
12235	116	18	is	be	VBZ
12235	116	19	not	not	RB
12235	116	20	corrected	correct	VBN
12235	116	21	,	,	,
12235	116	22	demonstrating	demonstrate	VBG
12235	116	23	an	an	DT
12235	116	24	increase	increase	NN
12235	116	25	in	in	IN
12235	116	26	terms	term	NNS
12235	116	27	omitted	omit	VBN
12235	116	28	for	for	IN
12235	116	29	entries	entry	NNS
12235	116	30	with	with	IN
12235	116	31	lower	low	JJR
12235	116	32	word	word	NN
12235	116	33	counts	count	NNS
12235	116	34	.	.	.
12235	117	1	These	these	DT
12235	117	2	results	result	NNS
12235	117	3	are	be	VBP
12235	117	4	broken	break	VBN
12235	117	5	down	down	RP
12235	117	6	by	by	IN
12235	117	7	vocabulary	vocabulary	NN
12235	117	8	used	use	VBN
12235	117	9	in	in	IN
12235	117	10	figure	figure	NN
12235	117	11	6	6	CD
12235	117	12	,	,	,
12235	117	13	demonstrating	demonstrate	VBG
12235	117	14	that	that	IN
12235	117	15	both	both	DT
12235	117	16	vocabularies	vocabulary	NNS
12235	117	17	used	use	VBD
12235	117	18	to	to	TO
12235	117	19	generate	generate	VB
12235	117	20	these	these	DT
12235	117	21	results	result	NNS
12235	117	22	indicate	indicate	VBP
12235	117	23	a	a	DT
12235	117	24	significant	significant	JJ
12235	117	25	increase	increase	NN
12235	117	26	in	in	IN
12235	117	27	omitted	omitted	JJ
12235	117	28	terms	term	NNS
12235	117	29	for	for	IN
12235	117	30	shorter	short	JJR
12235	117	31	entries	entry	NNS
12235	117	32	.	.	.
12235	118	1	Column1	Column1	NNP
12235	118	2	Both	both	DT
12235	118	3	Vocabularies	vocabulary	NNS
12235	118	4	2018	2018	CD
12235	118	5	LCSH	LCSH	NNP
12235	118	6	1910	1910	CD
12235	118	7	LCSH	LCSH	NNP
12235	118	8	Average	Average	NNP
12235	118	9	,	,	,
12235	118	10	Terms	term	NNS
12235	118	11	Omitted	omit	VBN
12235	118	12	6.73	6.73	CD
12235	118	13	3.67	3.67	CD
12235	118	14	3.07	3.07	CD
12235	118	15	Median	Median	NNP
12235	118	16	,	,	,
12235	118	17	Terms	term	NNS
12235	118	18	Omitted	omit	VBD
12235	118	19	5	5	CD
12235	118	20	3	3	CD
12235	118	21	2	2	CD
12235	118	22	Standard	Standard	NNP
12235	118	23	Deviation	deviation	NN
12235	118	24	6.53	6.53	CD
12235	118	25	3.84	3.84	CD
12235	118	26	3.17	3.17	CD
12235	118	27	Range	Range	NNP
12235	118	28	,	,	,
12235	118	29	Terms	term	NNS
12235	118	30	Omitted	omit	VBD
12235	118	31	0	0	CD
12235	118	32	-	-	SYM
12235	118	33	24	24	CD
12235	118	34	0	0	CD
12235	118	35	-	-	SYM
12235	118	36	13	13	CD
12235	118	37	0	0	CD
12235	118	38	-	-	HYPH
12235	118	39	11	11	CD
12235	118	40	Average	Average	NNP
12235	118	41	Percentage	percentage	NN
12235	118	42	,	,	,
12235	118	43	Omitted	Omitted	NNP
12235	118	44	Terms	term	NNS
12235	118	45	26.51	26.51	CD
12235	118	46	%	%	NN
12235	118	47	27.51	27.51	CD
12235	118	48	%	%	NN
12235	118	49	24.28	24.28	CD
12235	118	50	%	%	NN
12235	118	51	Median	median	JJ
12235	118	52	Percentage	Percentage	NNP
12235	118	53	,	,	,
12235	118	54	Omitted	Omitted	NNP
12235	118	55	Terms	term	NNS
12235	118	56	22.36	22.36	CD
12235	118	57	%	%	NN
12235	118	58	20.00	20.00	CD
12235	118	59	%	%	NN
12235	118	60	19.09	19.09	CD
12235	118	61	%	%	NN
12235	118	62	INFORMATION	information	NN
12235	118	63	TECHNOLOGY	technology	NN
12235	118	64	AND	and	CC
12235	118	65	LIBRARIES	library	NNS
12235	118	66	SEPTEMBER	SEPTEMBER	NNP
12235	118	67	2020	2020	CD
12235	118	68	EVALUATING	evaluate	VBG
12235	118	69	THE	the	DT
12235	118	70	IMPACT	impact	NN
12235	118	71	OF	of	IN
12235	118	72	THE	the	DT
12235	118	73	LONG	long	JJ
12235	118	74	-	-	HYPH
12235	118	75	S	s	NN
12235	118	76	|	|	NNP
12235	118	77	GRABUS	grabus	NN
12235	118	78	8	8	CD
12235	118	79	Figure	figure	NN
12235	118	80	5	5	CD
12235	118	81	.	.	.
12235	119	1	Number	number	NN
12235	119	2	of	of	IN
12235	119	3	automatic	automatic	JJ
12235	119	4	subject	subject	JJ
12235	119	5	indexing	indexing	NN
12235	119	6	terms	term	NNS
12235	119	7	that	that	WDT
12235	119	8	are	be	VBP
12235	119	9	omitted	omit	VBN
12235	119	10	when	when	WRB
12235	119	11	the	the	DT
12235	119	12	Long	Long	NNP
12235	119	13	-	-	HYPH
12235	119	14	S	S	NNP
12235	119	15	is	be	VBZ
12235	119	16	not	not	RB
12235	119	17	corrected	correct	VBN
12235	119	18	to	to	IN
12235	119	19	a	a	DT
12235	119	20	standard	standard	NN
12235	119	21	<	<	XX
12235	119	22	s	s	XX
12235	119	23	>	>	XX
12235	119	24	as	as	IN
12235	119	25	compared	compare	VBN
12235	119	26	by	by	IN
12235	119	27	encyclopedia	encyclopedia	NNS
12235	119	28	entry	entry	NN
12235	119	29	word	word	NN
12235	119	30	count	count	NN
12235	119	31	.	.	.
12235	120	1	Figure	figure	NN
12235	120	2	6	6	CD
12235	120	3	.	.	.
12235	121	1	Number	number	NN
12235	121	2	of	of	IN
12235	121	3	automatic	automatic	JJ
12235	121	4	subject	subject	JJ
12235	121	5	indexing	indexing	NN
12235	121	6	terms	term	NNS
12235	121	7	that	that	WDT
12235	121	8	are	be	VBP
12235	121	9	omitted	omit	VBN
12235	121	10	when	when	WRB
12235	121	11	the	the	DT
12235	121	12	Long	Long	NNP
12235	121	13	-	-	HYPH
12235	121	14	S	S	NNP
12235	121	15	is	be	VBZ
12235	121	16	not	not	RB
12235	121	17	corrected	correct	VBN
12235	121	18	to	to	IN
12235	121	19	a	a	DT
12235	121	20	standard	standard	NN
12235	121	21	<	<	XX
12235	121	22	s	s	XX
12235	121	23	>	>	XX
12235	121	24	as	as	IN
12235	121	25	compared	compare	VBN
12235	121	26	by	by	IN
12235	121	27	encyclopedia	encyclopedia	NNS
12235	121	28	entry	entry	NNP
12235	121	29	word	word	NN
12235	121	30	count	count	NN
12235	121	31	,	,	,
12235	121	32	separated	separate	VBN
12235	121	33	by	by	IN
12235	121	34	controlled	control	VBN
12235	121	35	vocabulary	vocabulary	JJ
12235	121	36	version	version	NN
12235	121	37	.	.	.
12235	122	1	INFORMATION	INFORMATION	NNP
12235	122	2	TECHNOLOGY	technology	NN
12235	122	3	AND	and	CC
12235	122	4	LIBRARIES	library	NNS
12235	122	5	SEPTEMBER	SEPTEMBER	NNP
12235	122	6	2020	2020	CD
12235	122	7	EVALUATING	evaluate	VBG
12235	122	8	THE	the	DT
12235	122	9	IMPACT	impact	NN
12235	122	10	OF	of	IN
12235	122	11	THE	the	DT
12235	122	12	LONG	long	JJ
12235	122	13	-	-	HYPH
12235	122	14	S	S	NNP
12235	122	15	|	|	NNP
12235	122	16	GRABUS	grabus	NN
12235	122	17	9	9	CD
12235	122	18	DISCUSSION	discussion	NN
12235	122	19	The	the	DT
12235	122	20	analysis	analysis	NN
12235	122	21	above	above	IN
12235	122	22	presents	present	VBZ
12235	122	23	measures	measure	NNS
12235	122	24	of	of	IN
12235	122	25	centrality	centrality	NN
12235	122	26	for	for	IN
12235	122	27	quantity	quantity	NN
12235	122	28	of	of	IN
12235	122	29	terms	term	NNS
12235	122	30	omitted	omit	VBN
12235	122	31	if	if	IN
12235	122	32	the	the	DT
12235	122	33	Long	Long	NNP
12235	122	34	-	-	HYPH
12235	122	35	S	S	NNP
12235	122	36	is	be	VBZ
12235	122	37	not	not	RB
12235	122	38	corrected	correct	VBN
12235	122	39	to	to	IN
12235	122	40	a	a	DT
12235	122	41	standard	standard	NN
12235	122	42	<	<	XX
12235	122	43	s	s	NNP
12235	122	44	>	>	XX
12235	122	45	prior	prior	RB
12235	122	46	to	to	IN
12235	122	47	automatic	automatic	JJ
12235	122	48	subject	subject	JJ
12235	122	49	indexing	indexing	NN
12235	122	50	using	use	VBG
12235	122	51	HIVE	HIVE	NNP
12235	122	52	,	,	,
12235	122	53	as	as	RB
12235	122	54	well	well	RB
12235	122	55	as	as	IN
12235	122	56	a	a	DT
12235	122	57	visualization	visualization	NN
12235	122	58	to	to	TO
12235	122	59	represent	represent	VB
12235	122	60	the	the	DT
12235	122	61	relationship	relationship	NN
12235	122	62	between	between	IN
12235	122	63	encyclopedia	encyclopedia	NNP
12235	122	64	entry	entry	NN
12235	122	65	word	word	NN
12235	122	66	count	count	NN
12235	122	67	and	and	CC
12235	122	68	number	number	NN
12235	122	69	of	of	IN
12235	122	70	terms	term	NNS
12235	122	71	omitted	omit	VBN
12235	122	72	.	.	.
12235	123	1	Although	although	IN
12235	123	2	researchers	researcher	NNS
12235	123	3	have	have	VBP
12235	123	4	identified	identify	VBN
12235	123	5	challenges	challenge	NNS
12235	123	6	with	with	IN
12235	123	7	the	the	DT
12235	123	8	Long	Long	NNP
12235	123	9	-	-	HYPH
12235	123	10	S	S	NNP
12235	123	11	and	and	CC
12235	123	12	have	have	VBP
12235	123	13	focused	focus	VBN
12235	123	14	a	a	DT
12235	123	15	great	great	JJ
12235	123	16	deal	deal	NN
12235	123	17	on	on	IN
12235	123	18	the	the	DT
12235	123	19	technologies	technology	NNS
12235	123	20	and	and	CC
12235	123	21	methods	method	NNS
12235	123	22	used	use	VBN
12235	123	23	to	to	TO
12235	123	24	correct	correct	VB
12235	123	25	it	-PRON-	PRP
12235	123	26	,	,	,
12235	123	27	there	there	EX
12235	123	28	is	be	VBZ
12235	123	29	still	still	RB
12235	123	30	limited	limited	JJ
12235	123	31	work	work	NN
12235	123	32	on	on	IN
12235	123	33	looking	look	VBG
12235	123	34	at	at	IN
12235	123	35	the	the	DT
12235	123	36	results	result	NNS
12235	123	37	of	of	IN
12235	123	38	not	not	RB
12235	123	39	correcting	correct	VBG
12235	123	40	the	the	DT
12235	123	41	Long	long	JJ
12235	123	42	-	-	HYPH
12235	123	43	S	S	NNP
12235	123	44	character	character	NN
12235	123	45	when	when	WRB
12235	123	46	performing	perform	VBG
12235	123	47	an	an	DT
12235	123	48	automatic	automatic	JJ
12235	123	49	subject	subject	JJ
12235	123	50	indexing	indexing	NN
12235	123	51	sequence	sequence	NN
12235	123	52	.	.	.
12235	124	1	This	this	DT
12235	124	2	research	research	NN
12235	124	3	demonstrated	demonstrate	VBD
12235	124	4	an	an	DT
12235	124	5	average	average	NN
12235	124	6	of	of	IN
12235	124	7	6.73	6.73	CD
12235	124	8	potentially	potentially	RB
12235	124	9	relevant	relevant	JJ
12235	124	10	terms	term	NNS
12235	124	11	omitted	omit	VBN
12235	124	12	from	from	IN
12235	124	13	automatic	automatic	JJ
12235	124	14	indexing	indexing	NN
12235	124	15	results	result	NNS
12235	124	16	when	when	WRB
12235	124	17	the	the	DT
12235	124	18	Long	Long	NNP
12235	124	19	-	-	HYPH
12235	124	20	S	S	NNP
12235	124	21	is	be	VBZ
12235	124	22	not	not	RB
12235	124	23	corrected	correct	VBN
12235	124	24	,	,	,
12235	124	25	accounting	account	VBG
12235	124	26	for	for	IN
12235	124	27	an	an	DT
12235	124	28	average	average	NN
12235	124	29	of	of	IN
12235	124	30	26.51	26.51	CD
12235	124	31	percent	percent	NN
12235	124	32	of	of	IN
12235	124	33	the	the	DT
12235	124	34	total	total	JJ
12235	124	35	results	result	NNS
12235	124	36	,	,	,
12235	124	37	with	with	IN
12235	124	38	an	an	DT
12235	124	39	approximately	approximately	RB
12235	124	40	equal	equal	JJ
12235	124	41	distribution	distribution	NN
12235	124	42	of	of	IN
12235	124	43	omitted	omit	VBN
12235	124	44	terms	term	NNS
12235	124	45	across	across	IN
12235	124	46	the	the	DT
12235	124	47	two	two	CD
12235	124	48	controlled	control	VBN
12235	124	49	vocabulary	vocabulary	JJ
12235	124	50	versions	version	NNS
12235	124	51	used	use	VBN
12235	124	52	.	.	.
12235	125	1	When	when	WRB
12235	125	2	the	the	DT
12235	125	3	quantity	quantity	NN
12235	125	4	of	of	IN
12235	125	5	terms	term	NNS
12235	125	6	omitted	omit	VBN
12235	125	7	is	be	VBZ
12235	125	8	visualized	visualize	VBN
12235	125	9	using	use	VBG
12235	125	10	a	a	DT
12235	125	11	continuous	continuous	JJ
12235	125	12	scatterplot	scatterplot	NN
12235	125	13	,	,	,
12235	125	14	the	the	DT
12235	125	15	results	result	NNS
12235	125	16	also	also	RB
12235	125	17	demonstrated	demonstrate	VBD
12235	125	18	a	a	DT
12235	125	19	significant	significant	JJ
12235	125	20	increase	increase	NN
12235	125	21	in	in	IN
12235	125	22	omitted	omitted	JJ
12235	125	23	terms	term	NNS
12235	125	24	for	for	IN
12235	125	25	shorter	short	JJR
12235	125	26	entries	entry	NNS
12235	125	27	,	,	,
12235	125	28	with	with	IN
12235	125	29	longer	long	JJR
12235	125	30	entries	entry	NNS
12235	125	31	less	less	RBR
12235	125	32	affected	affected	JJ
12235	125	33	.	.	.
12235	126	1	These	these	DT
12235	126	2	results	result	NNS
12235	126	3	reflect	reflect	VBP
12235	126	4	the	the	DT
12235	126	5	impact	impact	NN
12235	126	6	of	of	IN
12235	126	7	term	term	NN
12235	126	8	frequency	frequency	NN
12235	126	9	and	and	CC
12235	126	10	total	total	JJ
12235	126	11	word	word	NN
12235	126	12	count	count	NN
12235	126	13	in	in	IN
12235	126	14	keyword	keyword	NNP
12235	126	15	extraction	extraction	NNP
12235	126	16	and	and	CC
12235	126	17	automatic	automatic	JJ
12235	126	18	subject	subject	JJ
12235	126	19	indexing	indexing	NN
12235	126	20	,	,	,
12235	126	21	with	with	IN
12235	126	22	longer	long	JJR
12235	126	23	documents	document	NNS
12235	126	24	having	have	VBG
12235	126	25	a	a	DT
12235	126	26	greater	great	JJR
12235	126	27	pool	pool	NN
12235	126	28	of	of	IN
12235	126	29	total	total	JJ
12235	126	30	terms	term	NNS
12235	126	31	from	from	IN
12235	126	32	which	which	WDT
12235	126	33	to	to	TO
12235	126	34	identify	identify	VB
12235	126	35	key	key	JJ
12235	126	36	terms	term	NNS
12235	126	37	.	.	.
12235	127	1	Considering	consider	VBG
12235	127	2	the	the	DT
12235	127	3	complexities	complexity	NNS
12235	127	4	and	and	CC
12235	127	5	similarities	similarity	NNS
12235	127	6	of	of	IN
12235	127	7	the	the	DT
12235	127	8	typographical	typographical	JJ
12235	127	9	characters	character	NNS
12235	127	10	in	in	IN
12235	127	11	the	the	DT
12235	127	12	original	original	JJ
12235	127	13	manuscript	manuscript	NN
12235	127	14	,	,	,
12235	127	15	the	the	DT
12235	127	16	OCR	OCR	NNP
12235	127	17	output	output	NN
12235	127	18	process	process	NN
12235	127	19	for	for	IN
12235	127	20	this	this	DT
12235	127	21	corpus	corpus	NNP
12235	127	22	occasionally	occasionally	RB
12235	127	23	mistakes	mistake	VBZ
12235	127	24	the	the	DT
12235	127	25	letters	letter	NNS
12235	127	26	<	<	XX
12235	127	27	s	s	NNP
12235	127	28	>	>	XX
12235	127	29	,	,	,
12235	127	30	<	<	XX
12235	127	31	f	f	NNP
12235	127	32	>	>	XX
12235	127	33	,	,	,
12235	127	34	<	<	XX
12235	127	35	r	r	NNP
12235	127	36	>	>	XX
12235	127	37	,	,	,
12235	127	38	and	and	CC
12235	127	39	<	<	XX
12235	127	40	l	l	NNP
12235	127	41	>	>	XX
12235	127	42	.	.	.
12235	128	1	As	as	IN
12235	128	2	a	a	DT
12235	128	3	result	result	NN
12235	128	4	,	,	,
12235	128	5	an	an	DT
12235	128	6	occasional	occasional	JJ
12235	128	7	Long	long	JJ
12235	128	8	-	-	HYPH
12235	128	9	S	s	NN
12235	128	10	word	word	NN
12235	128	11	in	in	IN
12235	128	12	this	this	DT
12235	128	13	study	study	NN
12235	128	14	did	do	VBD
12235	128	15	not	not	RB
12235	128	16	originally	originally	RB
12235	128	17	contain	contain	VB
12235	128	18	an	an	DT
12235	128	19	<	<	XX
12235	128	20	s	s	XX
12235	128	21	>	>	XX
12235	128	22	(	(	-LRB-
12235	128	23	e.g.	e.g.	RB
12235	128	24	,	,	,
12235	128	25	sor	sor	NN
12235	128	26	instead	instead	RB
12235	128	27	of	of	IN
12235	128	28	for	for	IN
12235	128	29	)	)	-RRB-
12235	128	30	.	.	.
12235	129	1	Correction	correction	NN
12235	129	2	of	of	IN
12235	129	3	these	these	DT
12235	129	4	Long	long	JJ
12235	129	5	-	-	HYPH
12235	129	6	S	S	NNP
12235	129	7	OCR	OCR	NNP
12235	129	8	errors	error	NNS
12235	129	9	requires	require	VBZ
12235	129	10	the	the	DT
12235	129	11	development	development	NN
12235	129	12	of	of	IN
12235	129	13	a	a	DT
12235	129	14	dictionary	dictionary	NN
12235	129	15	-	-	HYPH
12235	129	16	based	base	VBN
12235	129	17	script	script	NN
12235	129	18	.	.	.
12235	130	1	An	an	DT
12235	130	2	additional	additional	JJ
12235	130	3	complication	complication	NN
12235	130	4	of	of	IN
12235	130	5	this	this	DT
12235	130	6	research	research	NN
12235	130	7	is	be	VBZ
12235	130	8	that	that	IN
12235	130	9	the	the	DT
12235	130	10	corrected	correct	VBN
12235	130	11	OCR	ocr	NN
12235	130	12	output	output	NN
12235	130	13	for	for	IN
12235	130	14	the	the	DT
12235	130	15	encyclopedia	encyclopedia	JJ
12235	130	16	entries	entry	NNS
12235	130	17	still	still	RB
12235	130	18	contains	contain	VBZ
12235	130	19	a	a	DT
12235	130	20	few	few	JJ
12235	130	21	errors	error	NNS
12235	130	22	not	not	RB
12235	130	23	related	relate	VBN
12235	130	24	to	to	IN
12235	130	25	the	the	DT
12235	130	26	Long	Long	NNP
12235	130	27	-	-	HYPH
12235	130	28	S	S	NNP
12235	130	29	,	,	,
12235	130	30	which	which	WDT
12235	130	31	will	will	MD
12235	130	32	prevent	prevent	VB
12235	130	33	the	the	DT
12235	130	34	mapping	mapping	NN
12235	130	35	of	of	IN
12235	130	36	the	the	DT
12235	130	37	term	term	NN
12235	130	38	to	to	IN
12235	130	39	any	any	DT
12235	130	40	controlled	controlled	JJ
12235	130	41	vocabulary	vocabulary	NN
12235	130	42	term	term	NN
12235	130	43	(	(	-LRB-
12235	130	44	e.g.	e.g.	RB
12235	130	45	,	,	,
12235	130	46	in	in	IN
12235	130	47	the	the	DT
12235	130	48	entry	entry	NN
12235	130	49	on	on	IN
12235	130	50	Sepulchre	Sepulchre	NNP
12235	130	51	,	,	,
12235	130	52	the	the	DT
12235	130	53	OCR	OCR	NNP
12235	130	54	output	output	NN
12235	130	55	for	for	IN
12235	130	56	the	the	DT
12235	130	57	term	term	NN
12235	130	58	Palestine	Palestine	NNP
12235	130	59	was	be	VBD
12235	130	60	Palestinc	Palestinc	NNP
12235	130	61	)	)	-RRB-
12235	130	62	.	.	.
12235	131	1	These	these	DT
12235	131	2	results	result	NNS
12235	131	3	are	be	VBP
12235	131	4	specific	specific	JJ
12235	131	5	to	to	IN
12235	131	6	this	this	DT
12235	131	7	particular	particular	JJ
12235	131	8	corpus	corpus	NN
12235	131	9	of	of	IN
12235	131	10	3rd	3rd	NNP
12235	131	11	edition	edition	NN
12235	131	12	Encyclopedia	Encyclopedia	NNP
12235	131	13	Britannica	Britannica	NNP
12235	131	14	entries	entrie	VBZ
12235	131	15	,	,	,
12235	131	16	but	but	CC
12235	131	17	it	-PRON-	PRP
12235	131	18	is	be	VBZ
12235	131	19	very	very	RB
12235	131	20	likely	likely	JJ
12235	131	21	that	that	IN
12235	131	22	testing	test	VBG
12235	131	23	another	another	DT
12235	131	24	set	set	NN
12235	131	25	of	of	IN
12235	131	26	pre-1800s	pre-1800s	``
12235	131	27	documents	document	NNS
12235	131	28	containing	contain	VBG
12235	131	29	the	the	DT
12235	131	30	Long	Long	NNP
12235	131	31	-	-	HYPH
12235	131	32	S	S	NNP
12235	131	33	would	would	MD
12235	131	34	also	also	RB
12235	131	35	illustrate	illustrate	VB
12235	131	36	that	that	IN
12235	131	37	for	for	IN
12235	131	38	best	good	JJS
12235	131	39	results	result	NNS
12235	131	40	with	with	IN
12235	131	41	any	any	DT
12235	131	42	algorithm	algorithm	NN
12235	131	43	or	or	CC
12235	131	44	tool	tool	NN
12235	131	45	,	,	,
12235	131	46	the	the	DT
12235	131	47	Long	Long	NNP
12235	131	48	-	-	HYPH
12235	131	49	S	S	NNP
12235	131	50	needs	need	VBZ
12235	131	51	to	to	TO
12235	131	52	be	be	VB
12235	131	53	corrected	correct	VBN
12235	131	54	.	.	.
12235	132	1	The	the	DT
12235	132	2	results	result	NNS
12235	132	3	are	be	VBP
12235	132	4	also	also	RB
12235	132	5	specific	specific	JJ
12235	132	6	to	to	IN
12235	132	7	the	the	DT
12235	132	8	two	two	CD
12235	132	9	versions	version	NNS
12235	132	10	of	of	IN
12235	132	11	the	the	DT
12235	132	12	LCSH	LCSH	NNP
12235	132	13	used	use	VBD
12235	132	14	,	,	,
12235	132	15	both	both	CC
12235	132	16	the	the	DT
12235	132	17	1910	1910	CD
12235	132	18	LCSH	LCSH	NNP
12235	132	19	and	and	CC
12235	132	20	the	the	DT
12235	132	21	2018	2018	CD
12235	132	22	LCSH	LCSH	NNP
12235	132	23	,	,	,
12235	132	24	which	which	WDT
12235	132	25	are	be	VBP
12235	132	26	available	available	JJ
12235	132	27	in	in	IN
12235	132	28	the	the	DT
12235	132	29	HIVE	HIVE	NNP
12235	132	30	tool	tool	NN
12235	132	31	.	.	.
12235	133	1	The	the	DT
12235	133	2	1910	1910	CD
12235	133	3	version	version	NN
12235	133	4	is	be	VBZ
12235	133	5	key	key	JJ
12235	133	6	for	for	IN
12235	133	7	the	the	DT
12235	133	8	time	time	NN
12235	133	9	period	period	NN
12235	133	10	being	be	VBG
12235	133	11	studied	study	VBN
12235	133	12	,	,	,
12235	133	13	and	and	CC
12235	133	14	the	the	DT
12235	133	15	2018	2018	CD
12235	133	16	,	,	,
12235	133	17	more	more	RBR
12235	133	18	contemporary	contemporary	JJ
12235	133	19	to	to	IN
12235	133	20	today	today	NN
12235	133	21	,	,	,
12235	133	22	has	have	VBZ
12235	133	23	supported	support	VBN
12235	133	24	additional	additional	JJ
12235	133	25	analysis	analysis	NN
12235	133	26	on	on	IN
12235	133	27	the	the	DT
12235	133	28	impact	impact	NN
12235	133	29	of	of	IN
12235	133	30	the	the	DT
12235	133	31	Long	Long	NNP
12235	133	32	-	-	HYPH
12235	133	33	S.	S.	NNP
12235	134	1	Both	both	DT
12235	134	2	of	of	IN
12235	134	3	these	these	DT
12235	134	4	vocabularies	vocabulary	NNS
12235	134	5	are	be	VBP
12235	134	6	important	important	JJ
12235	134	7	to	to	IN
12235	134	8	the	the	DT
12235	134	9	larger	large	JJR
12235	134	10	19th	19th	JJ
12235	134	11	-	-	HYPH
12235	134	12	Century	Century	NNP
12235	134	13	Knowledge	Knowledge	NNP
12235	134	14	Project	Project	NNP
12235	134	15	.	.	.
12235	135	1	It	-PRON-	PRP
12235	135	2	should	should	MD
12235	135	3	be	be	VB
12235	135	4	noted	note	VBN
12235	135	5	that	that	IN
12235	135	6	while	while	IN
12235	135	7	the	the	DT
12235	135	8	LCSH	LCSH	NNP
12235	135	9	is	be	VBZ
12235	135	10	updated	update	VBN
12235	135	11	weekly	weekly	RB
12235	135	12	,	,	,
12235	135	13	we	-PRON-	PRP
12235	135	14	were	be	VBD
12235	135	15	limited	limited	JJ
12235	135	16	to	to	IN
12235	135	17	what	what	WP
12235	135	18	is	be	VBZ
12235	135	19	available	available	JJ
12235	135	20	via	via	IN
12235	135	21	the	the	DT
12235	135	22	HIVE	HIVE	NNP
12235	135	23	tool	tool	NN
12235	135	24	,	,	,
12235	135	25	and	and	CC
12235	135	26	any	any	DT
12235	135	27	discrepancies	discrepancy	NNS
12235	135	28	that	that	WDT
12235	135	29	may	may	MD
12235	135	30	be	be	VB
12235	135	31	found	find	VBN
12235	135	32	with	with	IN
12235	135	33	the	the	DT
12235	135	34	2020	2020	CD
12235	135	35	LCSH	LCSH	NNP
12235	135	36	will	will	MD
12235	135	37	very	very	RB
12235	135	38	likely	likely	RB
12235	135	39	have	have	VB
12235	135	40	a	a	DT
12235	135	41	minimal	minimal	JJ
12235	135	42	effect	effect	NN
12235	135	43	upon	upon	IN
12235	135	44	metadata	metadata	NN
12235	135	45	generation	generation	NN
12235	135	46	results	result	NNS
12235	135	47	.	.	.
12235	136	1	It	-PRON-	PRP
12235	136	2	should	should	MD
12235	136	3	be	be	VB
12235	136	4	noted	note	VBN
12235	136	5	that	that	IN
12235	136	6	the	the	DT
12235	136	7	2020	2020	CD
12235	136	8	LCSH	LCSH	NNP
12235	136	9	will	will	MD
12235	136	10	be	be	VB
12235	136	11	incorporated	incorporate	VBN
12235	136	12	into	into	IN
12235	136	13	HIVE	HIVE	NNP
12235	136	14	soon	soon	RB
12235	136	15	and	and	CC
12235	136	16	can	can	MD
12235	136	17	be	be	VB
12235	136	18	explored	explore	VBN
12235	136	19	in	in	IN
12235	136	20	future	future	JJ
12235	136	21	research	research	NN
12235	136	22	.	.	.
12235	137	1	CONCLUSION	conclusion	NN
12235	137	2	AND	and	CC
12235	137	3	NEXT	NEXT	NNP
12235	137	4	STEPS	STEPS	NNP
12235	137	5	The	the	DT
12235	137	6	objective	objective	NN
12235	137	7	of	of	IN
12235	137	8	this	this	DT
12235	137	9	research	research	NN
12235	137	10	was	be	VBD
12235	137	11	to	to	TO
12235	137	12	determine	determine	VB
12235	137	13	the	the	DT
12235	137	14	impact	impact	NN
12235	137	15	of	of	IN
12235	137	16	correcting	correct	VBG
12235	137	17	the	the	DT
12235	137	18	Long	Long	NNP
12235	137	19	-	-	HYPH
12235	137	20	S	s	NN
12235	137	21	in	in	IN
12235	137	22	pre-1800s	pre-1800s	,
12235	137	23	documents	document	NNS
12235	137	24	when	when	WRB
12235	137	25	performing	perform	VBG
12235	137	26	an	an	DT
12235	137	27	automatic	automatic	JJ
12235	137	28	metadata	metadata	NN
12235	137	29	generation	generation	NN
12235	137	30	sequence	sequence	NN
12235	137	31	using	use	VBG
12235	137	32	keyword	keyword	NNP
12235	137	33	extraction	extraction	NNP
12235	137	34	and	and	CC
12235	137	35	controlled	control	VBN
12235	137	36	vocabulary	vocabulary	JJ
12235	137	37	mapping	mapping	NN
12235	137	38	.	.	.
12235	138	1	This	this	DT
12235	138	2	was	be	VBD
12235	138	3	accomplished	accomplish	VBN
12235	138	4	by	by	IN
12235	138	5	performing	perform	VBG
12235	138	6	an	an	DT
12235	138	7	automatic	automatic	JJ
12235	138	8	subject	subject	JJ
12235	138	9	indexing	indexing	NN
12235	138	10	sequence	sequence	NN
12235	138	11	using	use	VBG
12235	138	12	the	the	DT
12235	138	13	HIVE	HIVE	NNP
12235	138	14	tool	tool	NN
12235	138	15	,	,	,
12235	138	16	followed	follow	VBN
12235	138	17	by	by	IN
12235	138	18	a	a	DT
12235	138	19	basic	basic	JJ
12235	138	20	statistical	statistical	JJ
12235	138	21	analysis	analysis	NN
12235	138	22	to	to	TO
12235	138	23	determine	determine	VB
12235	138	24	the	the	DT
12235	138	25	quantity	quantity	NN
12235	138	26	of	of	IN
12235	138	27	terms	term	NNS
12235	138	28	omitted	omit	VBN
12235	138	29	from	from	IN
12235	138	30	the	the	DT
12235	138	31	results	result	NNS
12235	138	32	when	when	WRB
12235	138	33	the	the	DT
12235	138	34	Long	Long	NNP
12235	138	35	-	-	HYPH
12235	138	36	S	S	NNP
12235	138	37	is	be	VBZ
12235	138	38	not	not	RB
12235	138	39	corrected	correct	VBN
12235	138	40	to	to	IN
12235	138	41	a	a	DT
12235	138	42	standard	standard	NN
12235	138	43	<	<	XX
12235	138	44	s	s	NNP
12235	138	45	>	>	XX
12235	138	46	.	.	.
12235	139	1	The	the	DT
12235	139	2	number	number	NN
12235	139	3	of	of	IN
12235	139	4	omitted	omit	VBN
12235	139	5	terms	term	NNS
12235	139	6	was	be	VBD
12235	139	7	also	also	RB
12235	139	8	compared	compare	VBN
12235	139	9	with	with	IN
12235	139	10	the	the	DT
12235	139	11	encyclopedia	encyclopedia	NNS
12235	139	12	entry	entry	NN
12235	139	13	word	word	NN
12235	139	14	count	count	NN
12235	139	15	and	and	CC
12235	139	16	visualized	visualize	VBN
12235	139	17	to	to	TO
12235	139	18	demonstrate	demonstrate	VB
12235	139	19	a	a	DT
12235	139	20	significant	significant	JJ
12235	139	21	increase	increase	NN
12235	139	22	in	in	IN
12235	139	23	omitted	omitted	JJ
12235	139	24	terms	term	NNS
12235	139	25	for	for	IN
12235	139	26	shorter	short	JJR
12235	139	27	INFORMATION	information	NN
12235	139	28	TECHNOLOGY	technology	NN
12235	139	29	AND	and	CC
12235	139	30	LIBRARIES	library	NNS
12235	139	31	SEPTEMBER	SEPTEMBER	NNP
12235	139	32	2020	2020	CD
12235	139	33	EVALUATING	evaluate	VBG
12235	139	34	THE	the	DT
12235	139	35	IMPACT	impact	NN
12235	139	36	OF	of	IN
12235	139	37	THE	the	DT
12235	139	38	LONG	long	JJ
12235	139	39	-	-	HYPH
12235	139	40	S	S	NNP
12235	139	41	|	|	NNP
12235	139	42	GRABUS	grabus	NN
12235	139	43	10	10	CD
12235	139	44	encyclopedia	encyclopedia	NN
12235	139	45	entries	entry	NNS
12235	139	46	.	.	.
12235	140	1	The	the	DT
12235	140	2	study	study	NN
12235	140	3	was	be	VBD
12235	140	4	conclusive	conclusive	JJ
12235	140	5	in	in	IN
12235	140	6	confirming	confirm	VBG
12235	140	7	that	that	IN
12235	140	8	the	the	DT
12235	140	9	correction	correction	NN
12235	140	10	of	of	IN
12235	140	11	the	the	DT
12235	140	12	Long	Long	NNP
12235	140	13	-	-	HYPH
12235	140	14	S	S	NNP
12235	140	15	is	be	VBZ
12235	140	16	a	a	DT
12235	140	17	critical	critical	JJ
12235	140	18	part	part	NN
12235	140	19	of	of	IN
12235	140	20	our	-PRON-	PRP$
12235	140	21	workflow	workflow	NN
12235	140	22	.	.	.
12235	141	1	The	the	DT
12235	141	2	significance	significance	NN
12235	141	3	of	of	IN
12235	141	4	this	this	DT
12235	141	5	research	research	NN
12235	141	6	is	be	VBZ
12235	141	7	that	that	IN
12235	141	8	it	-PRON-	PRP
12235	141	9	demonstrates	demonstrate	VBZ
12235	141	10	the	the	DT
12235	141	11	necessity	necessity	NN
12235	141	12	of	of	IN
12235	141	13	correcting	correct	VBG
12235	141	14	the	the	DT
12235	141	15	Long	Long	NNP
12235	141	16	-	-	HYPH
12235	141	17	S	S	NNP
12235	141	18	prior	prior	RB
12235	141	19	to	to	IN
12235	141	20	performing	perform	VBG
12235	141	21	an	an	DT
12235	141	22	automatic	automatic	JJ
12235	141	23	subject	subject	JJ
12235	141	24	indexing	indexing	NN
12235	141	25	on	on	IN
12235	141	26	historical	historical	JJ
12235	141	27	documents	document	NNS
12235	141	28	.	.	.
12235	142	1	Beyond	beyond	IN
12235	142	2	the	the	DT
12235	142	3	correction	correction	NN
12235	142	4	of	of	IN
12235	142	5	the	the	DT
12235	142	6	Long	Long	NNP
12235	142	7	-	-	HYPH
12235	142	8	S	S	NNP
12235	142	9	,	,	,
12235	142	10	the	the	DT
12235	142	11	larger	large	JJR
12235	142	12	next	next	JJ
12235	142	13	steps	step	NNS
12235	142	14	for	for	IN
12235	142	15	this	this	DT
12235	142	16	project	project	NN
12235	142	17	are	be	VBP
12235	142	18	to	to	TO
12235	142	19	continue	continue	VB
12235	142	20	to	to	TO
12235	142	21	explore	explore	VB
12235	142	22	automatic	automatic	JJ
12235	142	23	metadata	metadata	NN
12235	142	24	generation	generation	NN
12235	142	25	for	for	IN
12235	142	26	this	this	DT
12235	142	27	corpus	corpus	NN
12235	142	28	.	.	.
12235	143	1	These	these	DT
12235	143	2	next	next	JJ
12235	143	3	steps	step	NNS
12235	143	4	include	include	VBP
12235	143	5	the	the	DT
12235	143	6	comparison	comparison	NN
12235	143	7	of	of	IN
12235	143	8	results	result	NNS
12235	143	9	using	use	VBG
12235	143	10	contemporary	contemporary	JJ
12235	143	11	vs.	vs.	IN
12235	143	12	historical	historical	JJ
12235	143	13	vocabularies	vocabulary	NNS
12235	143	14	and	and	CC
12235	143	15	streamlining	streamline	VBG
12235	143	16	a	a	DT
12235	143	17	protocol	protocol	NN
12235	143	18	for	for	IN
12235	143	19	bulk	bulk	JJ
12235	143	20	classification	classification	NN
12235	143	21	procedures	procedure	NNS
12235	143	22	and	and	CC
12235	143	23	integration	integration	NN
12235	143	24	of	of	IN
12235	143	25	terms	term	NNS
12235	143	26	into	into	IN
12235	143	27	the	the	DT
12235	143	28	TEI	tei	NN
12235	143	29	-	-	HYPH
12235	143	30	XML	xml	NN
12235	143	31	headers	header	NNS
12235	143	32	.	.	.
12235	144	1	The	the	DT
12235	144	2	research	research	NN
12235	144	3	presented	present	VBN
12235	144	4	here	here	RB
12235	144	5	can	can	MD
12235	144	6	inform	inform	VB
12235	144	7	other	other	JJ
12235	144	8	digital	digital	JJ
12235	144	9	humanities	humanity	NNS
12235	144	10	and	and	CC
12235	144	11	even	even	RB
12235	144	12	science	science	NN
12235	144	13	-	-	HYPH
12235	144	14	oriented	orient	VBN
12235	144	15	projects	project	NNS
12235	144	16	,	,	,
12235	144	17	where	where	WRB
12235	144	18	researchers	researcher	NNS
12235	144	19	may	may	MD
12235	144	20	not	not	RB
12235	144	21	be	be	VB
12235	144	22	aware	aware	JJ
12235	144	23	of	of	IN
12235	144	24	the	the	DT
12235	144	25	impact	impact	NN
12235	144	26	of	of	IN
12235	144	27	the	the	DT
12235	144	28	Long	Long	NNP
12235	144	29	-	-	HYPH
12235	144	30	S	S	NNP
12235	144	31	on	on	IN
12235	144	32	automatic	automatic	JJ
12235	144	33	metadata	metadata	NN
12235	144	34	generation	generation	NN
12235	144	35	not	not	RB
12235	144	36	only	only	RB
12235	144	37	for	for	IN
12235	144	38	subjects	subject	NNS
12235	144	39	,	,	,
12235	144	40	but	but	CC
12235	144	41	also	also	RB
12235	144	42	named	name	VBN
12235	144	43	entities	entity	NNS
12235	144	44	,	,	,
12235	144	45	particularly	particularly	RB
12235	144	46	when	when	WRB
12235	144	47	automatic	automatic	JJ
12235	144	48	approaches	approach	NNS
12235	144	49	with	with	IN
12235	144	50	controlled	controlled	JJ
12235	144	51	vocabularies	vocabulary	NNS
12235	144	52	are	be	VBP
12235	144	53	desired	desire	VBN
12235	144	54	.	.	.
12235	145	1	ACKNOWLEDGEMENTS	ACKNOWLEDGEMENTS	NNP
12235	145	2	The	the	DT
12235	145	3	author	author	NN
12235	145	4	thanks	thank	NNS
12235	145	5	Dr.	Dr.	NNP
12235	145	6	Jane	Jane	NNP
12235	145	7	Greenberg	Greenberg	NNP
12235	145	8	and	and	CC
12235	145	9	Dr.	Dr.	NNP
12235	145	10	Peter	Peter	NNP
12235	145	11	Logan	Logan	NNP
12235	145	12	for	for	IN
12235	145	13	their	-PRON-	PRP$
12235	145	14	guidance	guidance	NN
12235	145	15	.	.	.
12235	146	1	The	the	DT
12235	146	2	author	author	NN
12235	146	3	acknowledges	acknowledge	VBZ
12235	146	4	the	the	DT
12235	146	5	support	support	NN
12235	146	6	of	of	IN
12235	146	7	the	the	DT
12235	146	8	NEH	NEH	NNP
12235	146	9	grant	grant	NN
12235	146	10	#	#	NNP
12235	146	11	HAA-261228	HAA-261228	NNP
12235	146	12	-	-	HYPH
12235	146	13	18	18	CD
12235	146	14	.	.	.
12235	147	1	INFORMATION	INFORMATION	NNP
12235	147	2	TECHNOLOGY	technology	NN
12235	147	3	AND	and	CC
12235	147	4	LIBRARIES	library	NNS
12235	147	5	SEPTEMBER	SEPTEMBER	NNP
12235	147	6	2020	2020	CD
12235	147	7	EVALUATING	evaluate	VBG
12235	147	8	THE	the	DT
12235	147	9	IMPACT	impact	NN
12235	147	10	OF	of	IN
12235	147	11	THE	the	DT
12235	147	12	LONG	long	JJ
12235	147	13	-	-	HYPH
12235	147	14	S	S	NNP
12235	147	15	|	|	NNP
12235	147	16	GRABUS	grabus	NN
12235	147	17	11	11	CD
12235	147	18	APPENDIX	APPENDIX	NNP
12235	147	19	A	a	DT
12235	147	20	Entry	Entry	NNP
12235	147	21	Term	Term	NNP
12235	147	22	Total	Total	NNP
12235	147	23	Words	word	NNS
12235	147	24	Omitted	omit	VBN
12235	147	25	2018	2018	CD
12235	147	26	LCSH	LCSH	NNP
12235	147	27	Terms	term	NNS
12235	147	28	Omitted	omit	VBD
12235	147	29	1910	1910	CD
12235	147	30	LCSH	LCSH	NNP
12235	147	31	Terms	term	NNS
12235	147	32	Omitted	omit	VBD
12235	147	33	Encyclopedia	Encyclopedia	NNS
12235	147	34	Entry	entry	NN
12235	147	35	Word	word	NN
12235	147	36	Count	Count	NNP
12235	147	37	SARDIS	SARDIS	NNP
12235	147	38	24	24	CD
12235	147	39	13	13	CD
12235	147	40	11	11	CD
12235	147	41	381	381	CD
12235	147	42	SUCTION	suction	NN
12235	147	43	24	24	CD
12235	147	44	13	13	CD
12235	147	45	11	11	CD
12235	147	46	38	38	CD
12235	147	47	STYLITES	stylite	NNS
12235	147	48	,	,	,
12235	147	49	PILLAR	pillar	NN
12235	147	50	SAINTS	SAINTS	NNP
12235	147	51	19	19	CD
12235	147	52	13	13	CD
12235	147	53	6	6	CD
12235	147	54	199	199	CD
12235	147	55	SHADWELL	SHADWELL	NNP
12235	147	56	14	14	CD
12235	147	57	10	10	CD
12235	147	58	4	4	CD
12235	147	59	211	211	CD
12235	147	60	SALICORNIA	SALICORNIA	NNP
12235	147	61	13	13	CD
12235	147	62	6	6	CD
12235	147	63	7	7	CD
12235	147	64	254	254	CD
12235	147	65	SEPULCHRE	sepulchre	NN
12235	147	66	11	11	CD
12235	147	67	3	3	CD
12235	147	68	8	8	CD
12235	147	69	348	348	CD
12235	147	70	SITTA	sitta	NN
12235	147	71	NUTHATCH	nuthatch	NN
12235	147	72	9	9	CD
12235	147	73	5	5	CD
12235	147	74	4	4	CD
12235	147	75	620	620	CD
12235	147	76	SPRAT	SPRAT	NNS
12235	147	77	9	9	CD
12235	147	78	3	3	CD
12235	147	79	6	6	CD
12235	147	80	475	475	CD
12235	147	81	SERAPIS	SERAPIS	NNP
12235	147	82	8	8	CD
12235	147	83	5	5	CD
12235	147	84	3	3	CD
12235	147	85	587	587	CD
12235	147	86	STRADA	STRADA	NNP
12235	147	87	8	8	CD
12235	147	88	1	1	CD
12235	147	89	7	7	CD
12235	147	90	189	189	CD
12235	147	91	SHOAD	shoad	NN
12235	147	92	7	7	CD
12235	147	93	4	4	CD
12235	147	94	3	3	CD
12235	147	95	463	463	CD
12235	147	96	SIGN	sign	NN
12235	147	97	7	7	CD
12235	147	98	5	5	CD
12235	147	99	2	2	CD
12235	147	100	68	68	CD
12235	147	101	SHOOTING	shooting	SYM
12235	147	102	6	6	CD
12235	147	103	3	3	CD
12235	147	104	3	3	CD
12235	147	105	6114	6114	CD
12235	147	106	STRATA	STRATA	VBD
12235	147	107	6	6	CD
12235	147	108	3	3	CD
12235	147	109	3	3	CD
12235	147	110	2920	2920	CD
12235	147	111	STEWARTIA	STEWARTIA	VBN
12235	147	112	5	5	CD
12235	147	113	4	4	CD
12235	147	114	1	1	CD
12235	147	115	72	72	CD
12235	147	116	SUBCLAVIAN	SUBCLAVIAN	NNP
12235	147	117	5	5	CD
12235	147	118	3	3	CD
12235	147	119	2	2	CD
12235	147	120	20	20	CD
12235	147	121	SCHWEINFURT	schweinfurt	NN
12235	147	122	4	4	CD
12235	147	123	2	2	CD
12235	147	124	2	2	CD
12235	147	125	84	84	CD
12235	147	126	SCROLL	scroll	NN
12235	147	127	4	4	CD
12235	147	128	2	2	CD
12235	147	129	2	2	CD
12235	147	130	45	45	CD
12235	147	131	SPALATRO	SPALATRO	NNP
12235	147	132	4	4	CD
12235	147	133	3	3	CD
12235	147	134	1	1	CD
12235	147	135	99	99	CD
12235	147	136	SPECIAL	special	NN
12235	147	137	4	4	CD
12235	147	138	3	3	CD
12235	147	139	1	1	CD
12235	147	140	24	24	CD
12235	147	141	SAMOGITIA	SAMOGITIA	NNP
12235	147	142	3	3	CD
12235	147	143	2	2	CD
12235	147	144	1	1	CD
12235	147	145	112	112	CD
12235	147	146	SHAKESPEARE	shakespeare	NN
12235	147	147	3	3	CD
12235	147	148	0	0	CD
12235	147	149	3	3	CD
12235	147	150	3855	3855	CD
12235	147	151	SINAPISM	sinapism	NN
12235	147	152	2	2	CD
12235	147	153	1	1	CD
12235	147	154	1	1	CD
12235	147	155	25	25	CD
12235	147	156	SECT	SECT	NNS
12235	147	157	1	1	CD
12235	147	158	1	1	CD
12235	147	159	0	0	CD
12235	147	160	20	20	CD
12235	147	161	SEVERINO	severino	NN
12235	147	162	1	1	CD
12235	147	163	1	1	CD
12235	147	164	0	0	CD
12235	147	165	38	38	CD
12235	147	166	SHADDOCK	SHADDOCK	NNP
12235	147	167	1	1	CD
12235	147	168	1	1	CD
12235	147	169	0	0	CD
12235	147	170	6	6	CD
12235	147	171	SCARLET	SCARLET	NNP
12235	147	172	0	0	CD
12235	147	173	0	0	CD
12235	147	174	0	0	CD
12235	147	175	65	65	CD
12235	147	176	SHALLOP	shallop	NN
12235	147	177	,	,	,
12235	147	178	SHALLOOP	shalloop	NN
12235	147	179	0	0	NFP
12235	147	180	0	0	CD
12235	147	181	0	0	CD
12235	147	182	42	42	CD
12235	147	183	SOLDANELLA	soldanella	NN
12235	147	184	0	0	NFP
12235	147	185	0	0	CD
12235	147	186	0	0	CD
12235	147	187	56	56	CD
12235	147	188	SPOLETTO	spoletto	NN
12235	147	189	0	0	CD
12235	147	190	0	0	CD
12235	147	191	0	0	CD
12235	147	192	99	99	CD
12235	147	193	INFORMATION	information	NN
12235	147	194	TECHNOLOGY	technology	NN
12235	147	195	AND	and	CC
12235	147	196	LIBRARIES	library	NNS
12235	147	197	SEPTEMBER	SEPTEMBER	NNP
12235	147	198	2020	2020	CD
12235	147	199	EVALUATING	evaluate	VBG
12235	147	200	THE	the	DT
12235	147	201	IMPACT	impact	NN
12235	147	202	OF	of	IN
12235	147	203	THE	the	DT
12235	147	204	LONG	long	JJ
12235	147	205	-	-	HYPH
12235	147	206	S	S	NNP
12235	147	207	|	|	NNP
12235	147	208	GRABUS	grabus	NN
12235	147	209	12	12	CD
12235	147	210	APPENDIX	APPENDIX	NNP
12235	147	211	B	B	NNP
12235	147	212	*	*	NNP
12235	147	213	N	n	NN
12235	147	214	=	=	SYM
12235	147	215	30	30	CD
12235	147	216	entries	entry	NNS
12235	147	217	Average	average	JJ
12235	147	218	Terms	term	NNS
12235	147	219	Returned	return	VBD
12235	147	220	Median	median	JJ
12235	147	221	Terms	term	NNS
12235	147	222	Returned	return	VBD
12235	147	223	Corrected	Corrected	NNP
12235	147	224	24.77	24.77	CD
12235	147	225	/	/	SYM
12235	147	226	40	40	CD
12235	147	227	possible	possible	JJ
12235	147	228	28	28	CD
12235	147	229	/	/	SYM
12235	147	230	40	40	CD
12235	147	231	possible	possible	JJ
12235	147	232	Uncorrected	uncorrected	JJ
12235	147	233	26.47	26.47	CD
12235	147	234	/	/	SYM
12235	147	235	40	40	CD
12235	147	236	possible	possible	JJ
12235	147	237	29	29	CD
12235	147	238	/	/	SYM
12235	147	239	40	40	CD
12235	147	240	possible	possible	JJ
12235	147	241	2018	2018	CD
12235	147	242	LCSH	LCSH	NNP
12235	147	243	Corrected	correct	VBD
12235	147	244	14.10	14.10	CD
12235	147	245	/	/	SYM
12235	147	246	20	20	CD
12235	147	247	possible	possible	JJ
12235	147	248	19	19	CD
12235	147	249	/	/	SYM
12235	147	250	20	20	CD
12235	147	251	possible	possible	JJ
12235	147	252	2018	2018	CD
12235	147	253	LCSH	LCSH	NNP
12235	147	254	Uncorrected	Uncorrected	NNP
12235	147	255	13.47	13.47	CD
12235	147	256	/	/	SYM
12235	147	257	20	20	CD
12235	147	258	possible	possible	JJ
12235	147	259	18.5	18.5	CD
12235	147	260	/	/	SYM
12235	147	261	20	20	CD
12235	147	262	possible	possible	JJ
12235	147	263	1910	1910	CD
12235	147	264	LCSH	LCSH	NNP
12235	147	265	Corrected	correct	VBD
12235	147	266	11.27	11.27	CD
12235	147	267	/	/	SYM
12235	147	268	20	20	CD
12235	147	269	possible	possible	JJ
12235	147	270	11	11	CD
12235	147	271	/	/	SYM
12235	147	272	20	20	CD
12235	147	273	possible	possible	JJ
12235	147	274	1910	1910	CD
12235	147	275	LCSH	LCSH	NNP
12235	147	276	Uncorrected	uncorrected	JJ
12235	147	277	10.13	10.13	CD
12235	147	278	/	/	SYM
12235	147	279	20	20	CD
12235	147	280	possible	possible	JJ
12235	147	281	9	9	CD
12235	147	282	/	/	SYM
12235	147	283	20	20	CD
12235	147	284	possible	possible	JJ
12235	147	285	INFORMATION	information	JJ
12235	147	286	TECHNOLOGY	technology	NN
12235	147	287	AND	and	CC
12235	147	288	LIBRARIES	library	NNS
12235	147	289	SEPTEMBER	SEPTEMBER	NNP
12235	147	290	2020	2020	CD
12235	147	291	EVALUATING	evaluate	VBG
12235	147	292	THE	the	DT
12235	147	293	IMPACT	impact	NN
12235	147	294	OF	of	IN
12235	147	295	THE	the	DT
12235	147	296	LONG	long	JJ
12235	147	297	-	-	HYPH
12235	147	298	S	S	NNP
12235	147	299	|	|	NNP
12235	147	300	GRABUS	grabus	NN
12235	147	301	13	13	CD
12235	147	302	ENDNOTES	endnotes	NN
12235	147	303	1	1	CD
12235	147	304	Liz	Liz	NNP
12235	147	305	Woolcott	Woolcott	NNP
12235	147	306	,	,	,
12235	147	307	“	"	``
12235	147	308	Understanding	Understanding	NNP
12235	147	309	Metadata	Metadata	NNP
12235	147	310	:	:	:
12235	147	311	What	what	WP
12235	147	312	is	be	VBZ
12235	147	313	Metadata	Metadata	NNP
12235	147	314	,	,	,
12235	147	315	and	and	CC
12235	147	316	What	what	WP
12235	147	317	is	be	VBZ
12235	147	318	it	-PRON-	PRP
12235	147	319	For	for	IN
12235	147	320	?	?	.
12235	147	321	,	,	,
12235	147	322	”	"	''
12235	147	323	Routledge	Routledge	NNP
12235	147	324	(	(	-LRB-
12235	147	325	November	November	NNP
12235	147	326	17	17	CD
12235	147	327	,	,	,
12235	147	328	2017	2017	CD
12235	147	329	)	)	-RRB-
12235	147	330	,	,	,
12235	147	331	https://doi.org/10.1080/01639374.2017.1358232	https://doi.org/10.1080/01639374.2017.1358232	NNP
12235	147	332	;	;	:
12235	147	333	Koraljka	Koraljka	NNP
12235	147	334	Golub	Golub	NNP
12235	147	335	et	et	NNP
12235	147	336	al	al	NNP
12235	147	337	.	.	NNP
12235	147	338	,	,	,
12235	147	339	“	"	``
12235	147	340	A	a	DT
12235	147	341	framework	framework	NN
12235	147	342	for	for	IN
12235	147	343	evaluating	evaluate	VBG
12235	147	344	automatic	automatic	JJ
12235	147	345	indexing	indexing	NN
12235	147	346	or	or	CC
12235	147	347	classification	classification	NN
12235	147	348	in	in	IN
12235	147	349	the	the	DT
12235	147	350	context	context	NN
12235	147	351	of	of	IN
12235	147	352	retrieval	retrieval	NN
12235	147	353	,	,	,
12235	147	354	“	"	``
12235	147	355	Journal	Journal	NNP
12235	147	356	of	of	IN
12235	147	357	the	the	DT
12235	147	358	Association	Association	NNP
12235	147	359	for	for	IN
12235	147	360	Information	Information	NNP
12235	147	361	Science	Science	NNP
12235	147	362	and	and	CC
12235	147	363	Technology	Technology	NNP
12235	147	364	67	67	CD
12235	147	365	,	,	,
12235	147	366	no	no	UH
12235	147	367	.	.	.
12235	148	1	1	1	CD
12235	148	2	(	(	-LRB-
12235	148	3	2016	2016	CD
12235	148	4	)	)	-RRB-
12235	148	5	,	,	,
12235	148	6	https://doi.org/10.1002/asi.23600	https://doi.org/10.1002/asi.23600	NN
12235	148	7	;	;	:
12235	148	8	Lynne	Lynne	NNP
12235	148	9	C.	C.	NNP
12235	148	10	Howarth	Howarth	NNP
12235	148	11	,	,	,
12235	148	12	“	"	``
12235	148	13	Metadata	Metadata	NNP
12235	148	14	and	and	CC
12235	148	15	Bibliographic	Bibliographic	NNP
12235	148	16	Control	Control	NNP
12235	148	17	:	:	:
12235	148	18	Soul	Soul	NNP
12235	148	19	-	-	HYPH
12235	148	20	Mates	Mates	NNPS
12235	148	21	or	or	CC
12235	148	22	Two	Two	NNP
12235	148	23	Solitudes	Solitudes	NNPS
12235	148	24	?	?	.
12235	148	25	,	,	,
12235	148	26	“	"	``
12235	148	27	Cataloging	Cataloging	NNP
12235	148	28	&	&	CC
12235	148	29	Classification	Classification	NNP
12235	148	30	Quarterly	Quarterly	NNP
12235	148	31	40	40	CD
12235	148	32	,	,	,
12235	148	33	no	no	UH
12235	148	34	.	.	.
12235	149	1	3	3	CD
12235	149	2	-	-	SYM
12235	149	3	4	4	CD
12235	149	4	(	(	-LRB-
12235	149	5	2005	2005	CD
12235	149	6	)	)	-RRB-
12235	149	7	,	,	,
12235	149	8	https://doi.org/10.1300/J104v40n03_03	https://doi.org/10.1300/J104v40n03_03	NNP
12235	149	9	.	.	.
12235	150	1	2	2	CD
12235	150	2	A.	A.	NNP
12235	150	3	Belaid	Belaid	NNP
12235	150	4	et	et	NNP
12235	150	5	al	al	NNP
12235	150	6	.	.	NNP
12235	150	7	,	,	,
12235	150	8	“	"	``
12235	150	9	Automatic	automatic	JJ
12235	150	10	indexing	indexing	NN
12235	150	11	and	and	CC
12235	150	12	reformulation	reformulation	NN
12235	150	13	of	of	IN
12235	150	14	ancient	ancient	JJ
12235	150	15	dictionaries	dictionary	NNS
12235	150	16	“	"	''
12235	150	17	(	(	-LRB-
12235	150	18	paper	paper	NN
12235	150	19	presented	present	VBN
12235	150	20	at	at	IN
12235	150	21	the	the	DT
12235	150	22	First	First	NNP
12235	150	23	International	International	NNP
12235	150	24	Workshop	Workshop	NNP
12235	150	25	on	on	IN
12235	150	26	Document	Document	NNP
12235	150	27	Image	Image	NNP
12235	150	28	Analysis	Analysis	NNP
12235	150	29	for	for	IN
12235	150	30	Libraries	Libraries	NNPS
12235	150	31	,	,	,
12235	150	32	Palo	Palo	NNP
12235	150	33	Alto	Alto	NNP
12235	150	34	,	,	,
12235	150	35	CA	CA	NNP
12235	150	36	,	,	,
12235	150	37	2004	2004	CD
12235	150	38	)	)	-RRB-
12235	150	39	,	,	,
12235	150	40	https://doi.org/10.1109/DIAL.2004.1263264	https://doi.org/10.1109/DIAL.2004.1263264	NNP
12235	150	41	.	.	.
12235	151	1	3	3	CD
12235	151	2	Beatrice	Beatrice	NNP
12235	151	3	Alex	Alex	NNP
12235	151	4	et	et	FW
12235	151	5	al	al	NNP
12235	151	6	.	.	NNP
12235	151	7	,	,	,
12235	151	8	“	"	``
12235	151	9	Digitised	Digitised	NNP
12235	151	10	Historical	Historical	NNP
12235	151	11	Text	Text	NNP
12235	151	12	:	:	:
12235	151	13	Does	do	VBZ
12235	151	14	it	-PRON-	PRP
12235	151	15	have	have	VB
12235	151	16	to	to	TO
12235	151	17	be	be	VB
12235	151	18	mediOCRe	mediOCRe	NNP
12235	151	19	"	"	''
12235	151	20	(	(	-LRB-
12235	151	21	paper	paper	NN
12235	151	22	presented	present	VBN
12235	151	23	at	at	IN
12235	151	24	the	the	DT
12235	151	25	KONVENS	KONVENS	NNP
12235	151	26	2012	2012	CD
12235	151	27	(	(	-LRB-
12235	151	28	LThist	LThist	NNP
12235	151	29	2012	2012	CD
12235	151	30	workshop	workshop	NN
12235	151	31	)	)	-RRB-
12235	151	32	,	,	,
12235	151	33	Vienna	Vienna	NNP
12235	151	34	,	,	,
12235	151	35	September	September	NNP
12235	151	36	21	21	CD
12235	151	37	,	,	,
12235	151	38	2012	2012	CD
12235	151	39	)	)	-RRB-
12235	151	40	;	;	:
12235	151	41	Ted	Ted	NNP
12235	151	42	Underwood	Underwood	NNP
12235	151	43	,	,	,
12235	151	44	“	"	``
12235	151	45	A	a	DT
12235	151	46	half	half	JJ
12235	151	47	-	-	HYPH
12235	151	48	decent	decent	JJ
12235	151	49	OCR	ocr	NN
12235	151	50	normalizer	normalizer	NN
12235	151	51	for	for	IN
12235	151	52	English	English	NNP
12235	151	53	texts	text	NNS
12235	151	54	after	after	IN
12235	151	55	1700	1700	CD
12235	151	56	,	,	,
12235	151	57	"	"	``
12235	151	58	The	the	DT
12235	151	59	Stone	Stone	NNP
12235	151	60	and	and	CC
12235	151	61	the	the	DT
12235	151	62	Shell	Shell	NNP
12235	151	63	,	,	,
12235	151	64	December	December	NNP
12235	151	65	10	10	CD
12235	151	66	,	,	,
12235	151	67	2013	2013	CD
12235	151	68	,	,	,
12235	151	69	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-	NNP
12235	151	70	texts	text	NNS
12235	151	71	-	-	HYPH
12235	151	72	after-1700/.	after-1700/.	NNP
12235	152	1	4	4	LS
12235	152	2	“	"	``
12235	152	3	Nineteenth	nineteenth	JJ
12235	152	4	-	-	HYPH
12235	152	5	century	century	NN
12235	152	6	knowledge	knowledge	NN
12235	152	7	project	project	NN
12235	152	8	,	,	,
12235	152	9	"	"	''
12235	152	10	(	(	-LRB-
12235	152	11	GitHub	GitHub	NNP
12235	152	12	Repository	Repository	NNP
12235	152	13	)	)	-RRB-
12235	152	14	,	,	,
12235	152	15	2020	2020	CD
12235	152	16	,	,	,
12235	152	17	https://tu-	https://tu-	NN
12235	152	18	plogan.github.io/.	plogan.github.io/.	NNP
12235	153	1	5	5	LS
12235	153	2	“	"	``
12235	153	3	Nineteenth	nineteenth	JJ
12235	153	4	-	-	HYPH
12235	153	5	century	century	NN
12235	153	6	Knowledge	Knowledge	NNP
12235	153	7	Project	Project	NNP
12235	153	8	.	.	.
12235	153	9	”	"	''
12235	153	10	6	6	CD
12235	153	11	Marcia	Marcia	NNP
12235	153	12	Lei	Lei	NNP
12235	153	13	Zeng	Zeng	NNP
12235	153	14	and	and	CC
12235	153	15	Lois	Lois	NNP
12235	153	16	Mai	Mai	NNP
12235	153	17	Chan	Chan	NNP
12235	153	18	,	,	,
12235	153	19	“	"	``
12235	153	20	Metadata	Metadata	NNP
12235	153	21	Interoperability	Interoperability	NNP
12235	153	22	and	and	CC
12235	153	23	Standardization	Standardization	NNP
12235	153	24	-	-	HYPH
12235	153	25	A	A	NNP
12235	153	26	Study	Study	NNP
12235	153	27	of	of	IN
12235	153	28	Methodology	Methodology	NNP
12235	153	29	,	,	,
12235	153	30	Part	Part	NNP
12235	153	31	II	II	NNP
12235	153	32	,	,	,
12235	153	33	"	"	``
12235	153	34	D	D	NNP
12235	153	35	-	-	HYPH
12235	153	36	Lib	Lib	NNP
12235	153	37	Magazine	Magazine	NNP
12235	153	38	12	12	CD
12235	153	39	,	,	,
12235	153	40	no	no	UH
12235	153	41	.	.	.
12235	154	1	6	6	CD
12235	154	2	(	(	-LRB-
12235	154	3	2006	2006	CD
12235	154	4	)	)	-RRB-
12235	154	5	;	;	:
12235	154	6	G.	G.	NNP
12235	154	7	Bueno	Bueno	NNP
12235	154	8	-	-	HYPH
12235	154	9	de	de	NNP
12235	154	10	-	-	JJ
12235	154	11	la	la	JJ
12235	154	12	-	-	HYPH
12235	154	13	Fuente	Fuente	NNP
12235	154	14	,	,	,
12235	154	15	D.	D.	NNP
12235	154	16	Rodríguez	Rodríguez	NNP
12235	154	17	Mateos	Mateos	NNP
12235	154	18	,	,	,
12235	154	19	and	and	CC
12235	154	20	J.	J.	NNP
12235	154	21	Greenberg	Greenberg	NNP
12235	154	22	,	,	,
12235	154	23	“	"	``
12235	154	24	Chapter	chapter	NN
12235	154	25	10	10	CD
12235	154	26	-	-	HYPH
12235	154	27	Automatic	Automatic	NNP
12235	154	28	Text	Text	NNP
12235	154	29	Indexing	Indexing	NNP
12235	154	30	with	with	IN
12235	154	31	SKOS	SKOS	NNP
12235	154	32	Vocabularies	Vocabularies	NNPS
12235	154	33	in	in	IN
12235	154	34	HIVE	HIVE	NNP
12235	154	35	"	"	''
12235	154	36	(	(	-LRB-
12235	154	37	Elsevier	Elsevier	NNP
12235	154	38	Ltd	Ltd	NNP
12235	154	39	,	,	,
12235	154	40	2016	2016	CD
12235	154	41	)	)	-RRB-
12235	154	42	;	;	:
12235	154	43	Sheila	Sheila	NNP
12235	154	44	Bair	Bair	NNP
12235	154	45	and	and	CC
12235	154	46	Sharon	Sharon	NNP
12235	154	47	Carlson	Carlson	NNP
12235	154	48	,	,	,
12235	154	49	“	"	``
12235	154	50	Where	where	WRB
12235	154	51	Keywords	Keywords	NNPS
12235	154	52	Fail	Fail	NNP
12235	154	53	:	:	:
12235	154	54	Using	use	VBG
12235	154	55	Metadata	Metadata	NNP
12235	154	56	to	to	TO
12235	154	57	Facilitate	facilitate	VB
12235	154	58	Digital	Digital	NNP
12235	154	59	Humanities	Humanities	NNP
12235	154	60	Scholarship	Scholarship	NNP
12235	154	61	,	,	,
12235	154	62	"	"	''
12235	154	63	Journal	Journal	NNP
12235	154	64	of	of	IN
12235	154	65	Library	Library	NNP
12235	154	66	Metadata	Metadata	NNP
12235	154	67	8	8	CD
12235	154	68	,	,	,
12235	154	69	no	no	UH
12235	154	70	.	.	.
12235	155	1	3	3	CD
12235	155	2	(	(	-LRB-
12235	155	3	2008	2008	CD
12235	155	4	)	)	-RRB-
12235	155	5	,	,	,
12235	155	6	https://doi.org/10.1080/19386380802398503	https://doi.org/10.1080/19386380802398503	NNP
12235	155	7	.	.	.
12235	156	1	7	7	CD
12235	156	2	John	John	NNP
12235	156	3	Walsh	Walsh	NNP
12235	156	4	,	,	,
12235	156	5	“	"	``
12235	156	6	The	the	DT
12235	156	7	use	use	NN
12235	156	8	of	of	IN
12235	156	9	Library	Library	NNP
12235	156	10	of	of	IN
12235	156	11	Congress	Congress	NNP
12235	156	12	Subject	Subject	NNP
12235	156	13	Headings	Headings	NNPS
12235	156	14	in	in	IN
12235	156	15	digital	digital	JJ
12235	156	16	collections	collection	NNS
12235	156	17	,	,	,
12235	156	18	"	"	``
12235	156	19	Library	Library	NNP
12235	156	20	Review	Review	NNP
12235	156	21	60	60	CD
12235	156	22	,	,	,
12235	156	23	no	no	UH
12235	156	24	.	.	.
12235	157	1	4	4	CD
12235	157	2	(	(	-LRB-
12235	157	3	2011	2011	CD
12235	157	4	)	)	-RRB-
12235	157	5	,	,	,
12235	157	6	https://doi.org/10.1108/00242531111127875	https://doi.org/10.1108/00242531111127875	NNP
12235	157	7	.	.	.
12235	158	1	8	8	CD
12235	158	2	Jane	Jane	NNP
12235	158	3	Greenberg	Greenberg	NNP
12235	158	4	et	et	NNP
12235	158	5	al	al	NNP
12235	158	6	.	.	NNP
12235	158	7	,	,	,
12235	158	8	“	"	``
12235	158	9	HIVE	hive	RB
12235	158	10	:	:	:
12235	158	11	Helping	help	VBG
12235	158	12	interdisciplinary	interdisciplinary	JJ
12235	158	13	vocabulary	vocabulary	NN
12235	158	14	engineering	engineering	NN
12235	158	15	,	,	,
12235	158	16	“	"	``
12235	158	17	Bulletin	Bulletin	NNP
12235	158	18	of	of	IN
12235	158	19	the	the	DT
12235	158	20	American	American	NNP
12235	158	21	Society	Society	NNP
12235	158	22	for	for	IN
12235	158	23	Information	Information	NNP
12235	158	24	Science	Science	NNP
12235	158	25	and	and	CC
12235	158	26	Technology	Technology	NNP
12235	158	27	37	37	CD
12235	158	28	,	,	,
12235	158	29	no	no	UH
12235	158	30	.	.	.
12235	159	1	4	4	CD
12235	159	2	(	(	-LRB-
12235	159	3	2011	2011	CD
12235	159	4	)	)	-RRB-
12235	159	5	,	,	,
12235	159	6	https://doi.org/10.1002/bult.2011.1720370407	https://doi.org/10.1002/bult.2011.1720370407	NNP
12235	159	7	.	.	.
12235	160	1	9	9	CD
12235	160	2	Sam	Sam	NNP
12235	160	3	Grabus	Grabus	NNP
12235	160	4	et	et	FW
12235	160	5	al	al	NNP
12235	160	6	.	.	NNP
12235	160	7	,	,	,
12235	160	8	“	"	``
12235	160	9	Representing	represent	VBG
12235	160	10	Aboutness	Aboutness	NNP
12235	160	11	:	:	:
12235	160	12	Automatically	automatically	RB
12235	160	13	Indexing	indexing	NN
12235	160	14	19th-	19th-	NN
12235	160	15	Century	century	NN
12235	160	16	Encyclopedia	Encyclopedia	NNP
12235	160	17	Britannica	Britannica	NNP
12235	160	18	Entries	Entries	NNP
12235	160	19	,	,	,
12235	160	20	”	"	''
12235	160	21	NASKO	NASKO	NNP
12235	160	22	7	7	CD
12235	160	23	(	(	-LRB-
12235	160	24	2019	2019	CD
12235	160	25	)	)	-RRB-
12235	160	26	,	,	,
12235	160	27	pp	pp	NNP
12235	160	28	.	.	.
12235	161	1	138	138	CD
12235	161	2	-	-	SYM
12235	161	3	48	48	CD
12235	161	4	,	,	,
12235	161	5	https://doi.org/10.7152/nasko.v7i1.15635	https://doi.org/10.7152/nasko.v7i1.15635	NNP
12235	161	6	.	.	.
12235	162	1	10	10	CD
12235	162	2	Karen	Karen	NNP
12235	162	3	Attar	Attar	NNP
12235	162	4	,	,	,
12235	162	5	“	"	``
12235	162	6	S	S	NNP
12235	162	7	and	and	CC
12235	162	8	Long	Long	NNP
12235	162	9	S	S	NNP
12235	162	10	,	,	,
12235	162	11	"	"	''
12235	162	12	in	in	IN
12235	162	13	Oxford	Oxford	NNP
12235	162	14	Companion	Companion	NNP
12235	162	15	to	to	IN
12235	162	16	the	the	DT
12235	162	17	Book	Book	NNP
12235	162	18	,	,	,
12235	162	19	eds	eds	XX
12235	162	20	.	.	.
12235	163	1	Michael	Michael	NNP
12235	163	2	Felix	Felix	NNP
12235	163	3	Suarez	Suarez	NNP
12235	163	4	and	and	CC
12235	163	5	H.	H.	NNP
12235	163	6	R.	R.	NNP
12235	163	7	II	II	NNP
12235	163	8	Woudhuysen	Woudhuysen	NNP
12235	163	9	(	(	-LRB-
12235	163	10	Oxford	Oxford	NNP
12235	163	11	:	:	:
12235	163	12	Oxford	Oxford	NNP
12235	163	13	University	University	NNP
12235	163	14	Press	Press	NNP
12235	163	15	,	,	,
12235	163	16	2010	2010	CD
12235	163	17	)	)	-RRB-
12235	163	18	;	;	:
12235	163	19	Ingrid	Ingrid	NNP
12235	163	20	Tieken	Tieken	NNP
12235	163	21	-	-	HYPH
12235	163	22	Boon	Boon	NNP
12235	163	23	van	van	NNP
12235	163	24	Ostade	Ostade	NNP
12235	163	25	,	,	,
12235	163	26	“	"	``
12235	163	27	Spelling	spelling	NN
12235	163	28	systems	system	NNS
12235	163	29	,	,	,
12235	163	30	“	"	``
12235	163	31	in	in	IN
12235	163	32	An	an	DT
12235	163	33	Introduction	introduction	NN
12235	163	34	to	to	IN
12235	163	35	Late	late	JJ
12235	163	36	Modern	modern	JJ
12235	163	37	English	English	NNP
12235	163	38	(	(	-LRB-
12235	163	39	Edinburgh	Edinburgh	NNP
12235	163	40	University	University	NNP
12235	163	41	Press	Press	NNP
12235	163	42	,	,	,
12235	163	43	2009	2009	CD
12235	163	44	)	)	-RRB-
12235	163	45	.	.	.
12235	164	1	11	11	CD
12235	164	2	Andrew	Andrew	NNP
12235	164	3	West	West	NNP
12235	164	4	,	,	,
12235	164	5	“	"	``
12235	164	6	The	the	DT
12235	164	7	Rules	Rules	NNPS
12235	164	8	for	for	IN
12235	164	9	Long	Long	NNP
12235	164	10	-	-	HYPH
12235	164	11	S	S	NNP
12235	164	12	,	,	,
12235	164	13	"	"	''
12235	164	14	TUGboat	TUGboat	NNP
12235	164	15	32	32	CD
12235	164	16	,	,	,
12235	164	17	no	no	UH
12235	164	18	.	.	.
12235	165	1	1	1	CD
12235	165	2	(	(	-LRB-
12235	165	3	2011	2011	CD
12235	165	4	)	)	-RRB-
12235	165	5	.	.	.
12235	166	1	12	12	CD
12235	166	2	Attar	Attar	NNP
12235	166	3	,	,	,
12235	166	4	“	"	``
12235	166	5	S	S	NNP
12235	166	6	and	and	CC
12235	166	7	Long	Long	NNP
12235	166	8	S.	S.	NNP
12235	166	9	”	"	''
12235	166	10	https://doi.org/10.1080/01639374.2017.1358232	https://doi.org/10.1080/01639374.2017.1358232	NNP
12235	166	11	https://doi.org/10.1002/asi.23600	https://doi.org/10.1002/asi.23600	NN
12235	166	12	https://doi.org/10.1300/J104v40n03_03	https://doi.org/10.1300/j104v40n03_03	NN
12235	166	13	https://doi.org/10.1109/DIAL.2004.1263264	https://doi.org/10.1109/DIAL.2004.1263264	.
12235	166	14	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	-LRB-
12235	166	15	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	-LRB-
12235	166	16	https://tu-plogan.github.io/	https://tu-plogan.github.io/	NFP
12235	166	17	https://tu-plogan.github.io/	https://tu-plogan.github.io/	NFP
12235	166	18	https://doi.org/10.1080/19386380802398503	https://doi.org/10.1080/19386380802398503	UH
12235	166	19	https://doi.org/10.1108/00242531111127875	https://doi.org/10.1108/00242531111127875	.
12235	166	20	https://doi.org/10.1002/bult.2011.1720370407	https://doi.org/10.1002/bult.2011.1720370407	NNP
12235	166	21	https://doi.org/10.7152/nasko.v7i1.15635	https://doi.org/10.7152/nasko.v7i1.15635	NNP
12235	166	22	ABSTRACT	abstract	JJ
12235	166	23	INTRODUCTION	introduction	NN
12235	166	24	Background	background	NN
12235	166	25	Indexing	indexing	NN
12235	166	26	for	for	IN
12235	166	27	the	the	DT
12235	166	28	19th	19th	JJ
12235	166	29	-	-	HYPH
12235	166	30	Century	Century	NNP
12235	166	31	Knowledge	Knowledge	NNP
12235	166	32	Project	Project	NNP
12235	166	33	The	the	DT
12235	166	34	Long	Long	NNP
12235	166	35	-	-	HYPH
12235	166	36	S	S	NNP
12235	166	37	Problem	problem	NN
12235	166	38	Encyclopedia	encyclopedia	NN
12235	166	39	Entry	entry	NN
12235	166	40	Lengths	length	VBZ
12235	166	41	Objectives	Objectives	NNP
12235	166	42	Methods	Methods	NNP
12235	166	43	Results	Results	NNPS
12235	166	44	Discussion	Discussion	NNP
12235	166	45	Conclusion	Conclusion	NNP
12235	166	46	and	and	CC
12235	166	47	Next	Next	NNP
12235	166	48	Steps	Steps	NNPS
12235	166	49	Acknowledgements	Acknowledgements	NNPS
12235	166	50	Appendix	Appendix	NNP
12235	166	51	A	a	DT
12235	166	52	Appendix	Appendix	NNP
12235	166	53	B	b	NN