id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_k6wfvskhsjdfzbbrhtoyfkwd7a	Md Arafat Sultan	Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence	2014	12	.pdf	application/pdf	7471	741	63	Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence Back to Basics for Monolingual Alignment: Exploiting Word Similarity and aligning similar semantic units in a pair of sentences they found contextual evidence in the form of syntactic constraints useful in better aligning stop words. a central component of most aligners; various measures of word similarity have been utilized, including We apply the notion of dependency type equivalence to intra-category alignment of content words dependencies.) Given a word pair (si, tj) from the input sentences S and T , it collects contextual evidence and align all identical word sequence pairs in S and Note that in cwTextAlign we also align semantically similar content word pairs (si, tj) with no contextual similarities if no pairs (sk, tj) or (si, tl) exist word alignments are dependent on existing content similarity: a) aligned content word proportion, b) the	./cache/work_k6wfvskhsjdfzbbrhtoyfkwd7a.pdf	./txt/work_k6wfvskhsjdfzbbrhtoyfkwd7a.txt