Paper: Which Are the Best Features for Automatic Verb Classification

ACL ID P08-1050
Title Which Are the Best Features for Automatic Verb Classification
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

In this work, we develop and evaluate a wide range of feature spaces for deriving Levin- style verb classifications (Levin, 1993). We perform the classification experiments using Bayesian Multinomial Regression (an effi- cient log-linear modeling framework which we found to outperform SVMs for this task) with the proposed feature spaces. Our exper- iments suggest that subcategorization frames are not the most effective features for auto- matic verb classification. A mixture of syntac- tic information and lexical information works best for this task.