id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_5sg54cik6vhyno33zefmwbmjyy	Željko Agić	Multilingual Projection for Parsing Truly Low-Resource Languages	2016	12	.pdf	application/pdf	7470	765	69	part-of-speech tagging and dependency parsing for truly low-resource languages. Our annotation projection-based approach yields tagging and parsing models for over 100 languages. The best cross-lingual dependency parsing results reported to date were presented by Rasooli and Collins (2015). to cross-lingual POS tagging and dependency parsing are biased toward Indo-European languages, in annotations projected from one or more source sentences through word alignments. Figure 1: An outline of dependency annotation projection, voting, and decoding in our method, using two sources i each vertex v, the projection works by gathering evidence for each tag from all source tokens aligned to Languages with more than 60k tokens (in the training data) are considered source languages, the remaining 6 smaller treebanks (Estonian, Greek, Hungarian, Latin, Romanian, Tamil) are strictly considered targets. sentence pairs, we project POS tags and dependency and dependency parsed target sentence ready to contribute in training a tagger and parser.	./cache/work_5sg54cik6vhyno33zefmwbmjyy.pdf	./txt/work_5sg54cik6vhyno33zefmwbmjyy.txt