Paper: Recognizing Causality in Verb-Noun Pairs via Noun and Verb Semantics

ACL ID W14-0707
Title Recognizing Causality in Verb-Noun Pairs via Noun and Verb Semantics
Venue Workshop on Computational Approaches to Causality in Language
Session
Year 2014
Authors

Several supervised approaches have been proposed for causality identification by re- lying on shallow linguistic features. How- ever, such features do not lead to improved performance. Therefore, novel sources of knowledge are required to achieve progress on this problem. In this paper, we propose a model for the recognition of causality in verb-noun pairs by employing additional types of knowledge along with linguistic features. In particular, we fo- cus on identifying and employing seman- tic classes of nouns and verbs with high tendency to encode cause or non-cause re- lations. Our model incorporates the in- formation about these classes to minimize errors in predictions made by a basic su- pervised classifier relying merely on shal- low linguistic features. As compared with this basic ...