Computational Lexicography and Lexicology A Large-Scale Extension of VerbNet with Novel Verb Classes

Lexical classifications have proved useful in supporting various linguistic and natural language processing (NLP) tasks. The largest verb classification in English is Levin's (1993) work. VerbNet (Kipper-Schuler 2006) the largest computational verb lexicon currently available for English provides detailed syntactic-semantic descriptions of Levin classes. While the classes included are extensive enough for some NLP use, they are not comprehensive. Korhonen and Briscoe (2004) have proposed a significant extension of Levin's classification which incorporates 57 novel classes for verbs not covered (comprehensively) by Levin. Korhonen and Ryant (2005) have recently supplemented this with another extension including 53 additional classes. This paper describes the integration of these two extensions into VerbNet. The result is an extensive Levin style classification for English verbs which now provides over 90% token coverage of the PropBank data, making possible the use of supervised machine learning.