id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_4wuutuv2lfhhdgl2dgr6ruegii	Mengqiu Wang	Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning	2014	12	.pdf	application/pdf	7128	829	68	Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning labeled examples, our method yields significant improvements over state-of-the-art supervised methods, achieving best reported numbers to date on Chinese OntoNotes and German CoNLL-03 datasets. (2001) project labels produced by an English tagger to the foreign side of bitext, then use the projected labels to learn a HMM model. Given bitext between English and a foreign language, our goal is to learn a CRF model in the Figure 1: Diagram illustrating the projection of model expectation from English to Chinese. We would like to learn a CRF model in the foreign language that has similar expectations as the Projecting expectations instead of one-best label assignments from English to foreign language can the weakly supervised setting, we simulate the condition of having no labeled training data, and evaluate the model learned from bitext alone. our method, learned over bitext alone, can rival performance of supervised models trained with thousands of labeled examples.	./cache/work_4wuutuv2lfhhdgl2dgr6ruegii.pdf	./txt/work_4wuutuv2lfhhdgl2dgr6ruegii.txt