id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ql5liv4nfjah5lwcdnfg2r7ypm	Rui Cai	Syntax-aware Semantic Role Labeling without Parsing	2019	14	.pdf	application/pdf	8805	1032	57	aware representations for semantic role labeling without recourse to an external parser. The backbone of our model is an LSTMbased semantic role labeler jointly trained with the arguments of semantic predicates in a sentence and label them with a set of predefined whose semantic role annotations have been produced on top of treebanked corpora, and as a result are closely tied to syntactic information. (2018) incorporate syntactic information in a multi-task neural network model that semantic role labeler jointly trained with a dependency information extractor with two auxiliary tasks: predicting the dependency label of serves as input (combined with word representations) to the semantic role labeler. • a word representation component that encapsulates predicate-specific dependency Figure 2: Model overview: Dependency information extractor (bottom) and a semantic role labeler (top). semantic role labeler and the dependency extractor. multi-task learning in order to make use of linguistic information for semantic role labeling as	./cache/work_ql5liv4nfjah5lwcdnfg2r7ypm.pdf	./txt/work_ql5liv4nfjah5lwcdnfg2r7ypm.txt