Improving Semantic Role Labeling with Word Sense

Semantic role labeling (SRL) not only needs lexical and syntactic information, but also needs word sense information. However, because of the lack of corpus annotated with both word senses and semantic roles, there is few research on using word sense for SRL. The release of OntoNotes provides an opportunity for us to study how to use word sense for SRL. In this paper, we present some novel word sense features for SRL and find that they can improve the performance significantly.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Wanxiang Che, Ting Liu, Yongqiang Li
• Keywords: Computational Linguistics, NAACL 2010, Semantic Roles, Word Sense, Word Sense Information