id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_44qds2wxfnh3tncnwfvuffhoau	Mohammad Sadegh Rasooli	Cross-Lingual Syntactic Transfer with Limited Resources	2017	16	.pdf	application/pdf	10082	1158	75	language treebanks; 3) a method for integrating these steps with the density-driven annotation projection method of Rasooli and Collins source of translation data is the Bible, a considerably smaller corpus than the Europarl 2016) and methods that leverage cross-lingual representations of word clusters, embeddings or dictionaries (Täckström et al., 2012; Durrett et al., 2012; • We describe a method for transfer of lexical information from the target language into source When using Europarl data instead of the Bible, our approach gives 83.9% accuracy, a 1.7% absolute improvement over Rasooli and Our experiments showed an improvement in average labeled dependency accuracy for the languages We can use the cluster-based features φ(c)(x,y) on the source language treebanks Table 6: Results for our method using different sources of translation data. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1234–1244,	./cache/work_44qds2wxfnh3tncnwfvuffhoau.pdf	./txt/work_44qds2wxfnh3tncnwfvuffhoau.txt