id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_liz65ql5sngstk6qo3rdxliyw4	John Wieting	From Paraphrase Database to Compositional Paraphrase Model and Back	2015	14	.pdf	application/pdf	9030	799	66	The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with We address these issues in this work by introducing ways to use PPDB to construct parametric paraphrase models. We find improved performance by training a recursive neural network (RNN; Socher et al., 2010) directly on phrase pairs from PPDB. We show that our resulting word and phrase representations are effective on a wide variety of tasks, PPDB phrase pairs and evaluates how well models We created two novel datasets: (1) AnnotatedPPDB, a subset of phrase pairs from PPDB which to establish a way to evaluate compositional paraphrase models on short phrases. For training, we extracted word pairs from the lexical XL section of PPDB. Table 8: Illustrative phrase pairs from Annotated-PPDB with gold similarity > 4.	./cache/work_liz65ql5sngstk6qo3rdxliyw4.pdf	./txt/work_liz65ql5sngstk6qo3rdxliyw4.txt