A general feature space for automatic verb classification

  1. Get@NRC: A general feature space for automatic verb classification (Opens in a new window)
DOIResolve DOI: http://doi.org/10.1017/S135132490600444X
AuthorSearch for: ; Search for: ; Search for:
Journal titleNatural Language Engineering
AbstractLexical semantic classes of verbs play an important role in structuring complex predicate information in a lexicon, thereby avoiding redundancy and enabling generalizations across semantically similar verbs with respect to their usage. Such classes, however, require many person-years of expert effort to create manually, and methods are needed for automatically assigning verbs to appropriate classes. In this work, we develop and evaluate a feature space to support the automatic assignment of verbs into a well-known lexical semantic classification that is frequently used in natural language processing. The feature space is general – applicable to any class distinctions within the target classification; broad – tapping into a variety of semantic features of the classes; and inexpensive – requiring no more than a POS tagger and chunker. We perform experiments using support vector machines (SVMs) with the proposed feature space, demonstrating a reduction in error rate ranging from 48% to 88% over a chance baseline accuracy, across classification tasks of varying difficulty. In particular, we attain performance comparable to or better than that of feature sets manually selected for the particular tasks. Our results show that the approach is generally applicable, and reduces the need for resource-intensive linguistic analysis for each new classification task. We also perform a wide range of experiments to determine the most informative features in the feature space, finding that simple, easily extractable features suffice for good verb classification performance.
Publication date
AffiliationNational Research Council Canada
Peer reviewedNo
NRC publication
This is a non-NRC publication

"Non-NRC publications" are publications authored by NRC employees prior to their employment by NRC.

NPARC number23000813
Export citationExport as RIS
Report a correctionReport a correction
Record identifier5b25f803-8b1b-4da2-ad35-6e27cfc90ac2
Record created2016-10-14
Record modified2016-10-14
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)