Paper: On WordNet Semantic Classes and Dependency Parsing

ACL ID P14-2106
Title On WordNet Semantic Classes and Dependency Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014

This paper presents experiments with WordNet semantic classes to improve de- pendency parsing. We study the effect of semantic classes in three dependency parsers, using two types of constituency- to-dependency conversions of the English Penn Treebank. Overall, we can say that the improvements are small and not sig- nificant using automatic POS tags, con- trary to previously published results using gold POS tags (Agirre et al., 2011). In addition, we explore parser combinations, showing that the semantically enhanced parsers yield a small significant gain only on the more semantically oriented LTH treebank conversion.