Work

Extending VerbNet with Novel Verb Classes

Year: 2006

Type: conference-paper

Abstract: Lexical classifications have proved useful in supporting various natural language processing (NLP) tasks.The largest verb classification for English is Levin's (1993) work which defined groupings of verbs based on syntactic properties.VerbNet (Kipper et al., 2000;Kipper-Schuler, 2005) -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.This paper describes the integration of these classes into VerbNet.The result is the most extensive Levin-style classification for English verbs which can be highly useful for practical applications.

Source: Language Resources and Evaluation Conference (LREC)

DOI: 10.63317/2z6m7csxuxbs

Authors: Karin Kipper, Anna Korhonen, Neville Ryant, Martha Palmer

Institutions: University of Pennsylvania, University of Cambridge, University of Colorado Boulder

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, University of Pennsylvania, Defense Advanced Research Projects Agency, University of Illinois at Urbana-Champaign

Awards: G1037014486, Advancing the Performance of Word Sense Disambiguation by Finding Consistent Criteria for Sense Distinctions, MLIAM: ISLE-International Standards for Language Engineering, Associating Semantic features with Intersective Levin classes