Class-Based Construction of a Verb Lexicon

Abstract

We present an approach to building a verb lexicon compatible with WordNet but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically construct lexical entries. By using verb classes we capture generalizations about verb behavior and reduce the effort needed to construct the lexicon. The syntactic frames for the verb classes are represented by a Lexicalized Tree Adjoining Grammar augmented with semantic predicates, which allows a compositional interpretation. Introduction Despite many different approaches to lexicon development (Pustejovsky 1991), (Copestake & Sanfilippo 1993), (Lowe, Baker, & Fillmore 1997), (Dorr 1997), the field of Natural Language Processing (NLP) has yet to develop a clear consensus on guidelines for computational verb lexicons, which has severely limited their utility in NLP applications. Many approaches make no attempt to associate the semantics of a verb with its possible syntactic frames. Others list too...

Cite

Text

Kipper et al. "Class-Based Construction of a Verb Lexicon." AAAI Conference on Artificial Intelligence, 2000.

Markdown

[Kipper et al. "Class-Based Construction of a Verb Lexicon." AAAI Conference on Artificial Intelligence, 2000.](https://mlanthology.org/aaai/2000/kipper2000aaai-class/)

BibTeX

@inproceedings{kipper2000aaai-class,
  title     = {{Class-Based Construction of a Verb Lexicon}},
  author    = {Kipper, Karin and Dang, Hoa Trang and Palmer, Martha Stone},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2000},
  pages     = {691-696},
  url       = {https://mlanthology.org/aaai/2000/kipper2000aaai-class/}
}