Verb Class Discovery from Rich Syntactic Data

Abstract. Previous research has shown that syntactic features are the most informative features in automatic verb classification. We investigate their optimal characteristics by comparing a range of feature sets extracted from data where the proportion of verbal arguments and adjuncts is controlled. The data are obtained from different versions of VALEX [1]

• Type: Conference
• Year: 2008
• Where: CICLING
• Authors: Lin Sun, Anna Korhonen, Yuval Krymolowski
• Keywords: Automatic Verb Classification, CICLING 2008, Feature Set, Large Scf Lexicon, Natural Language Processing