id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
github-com-2813		GitHub - cmoa/teenie-week-of-play: Documents a one week intensive focussed on scripting and testing experimental code to document the limitations and capabilities of machine learning, text parsing, and crowdsourcing technologies on making a meaningful contribution to the archival metadata of the Teenie Harris collection.			.html	text/html	2100	203	68	GitHub cmoa/teenie-week-of-play: Documents a one week intensive focussed on scripting and testing experimental code to document the limitations and capabilities of machine learning, text parsing, and crowdsourcing technologies on making a meaningful contribution to the archival metadata of the Teenie Harris collection. During the week we explored four areas: Auto shortening titles, cleaning up existing subject headings, extracting names and locations from descriptions using Named Entity Recognition (NER), and verifying face recognition data using Amazon Mechanical Turk. Documents a one week intensive focussed on scripting and testing experimental code to document the limitations and capabilities of machine learning, text parsing, and crowdsourcing technologies on making a meaningful contribution to the archival metadata of the Teenie Harris collection. Documents a one week intensive focussed on scripting and testing experimental code to document the limitations and capabilities of machine learning, text parsing, and crowdsourcing technologies on making a meaningful contribution to the archival metadata of the Teenie Harris collection.	./cache/github-com-2813.html	./txt/github-com-2813.txt