id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_57lneblzxjhgdbzxcmcswlxbxu	Haitong Yang	Domain Adaptation for Syntactic and Semantic Dependency Parsing Using Deep Belief Networks	2015	12	.pdf	application/pdf	7358	722	70	Domain Adaptation for Syntactic and Semantic Dependency Parsing Using In current systems for syntactic and semantic dependency parsing, people usually define a very high-dimensional feature space to With additional unlabeled target domain data, our method can learn a latent feature representation (LFR) that is beneficial to For example, the relation path between a predicate and an argument is a syntactic feature used in semantic dependency parsing (Johansson and Nugues, 2008). Our DBN model is trained unsupervisedly on original feature vectors of data in both domains: training data from the source domain, and unlabeled data Using the original features, the performance drop on out-of-domain test data is 10.58 section, we introduce how our DBN model represent a data sample as a vector of latent features. data to our DBN model, we learn the LFR for semantic dependency parsing. the training time of our DBN models for both syntactic and semantic parsing.	./cache/work_57lneblzxjhgdbzxcmcswlxbxu.pdf	./txt/work_57lneblzxjhgdbzxcmcswlxbxu.txt