A general feature space for automatic verb classification. Joanis, E., Stevenson, S., & James, D. Natural Language Engineering, 14(3):337–367, 2008. Also published by Cambridge Journals Online on December 19, 2006
abstract   bibtex   
Lexical 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.
@Article{	  joanis1,
  author	= {Eric Joanis and Suzanne Stevenson and David James},
  title		= {A general feature space for automatic verb classification},
  journal	= {Natural Language Engineering},
  volume	= {14},
  number	= {3},
  pages		= {337--367},
  year		= {2008},
  note		= {Also published by <a
		  href=http://journals.cambridge.org/action/displayIssue?jid=NLE&volumeId=14&issueId=03>Cambridge
		  Journals Online</A> on December 19, 2006},
  abstract	= {Lexical 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
		  <em>general</em> &ndash; applicable to any class
		  distinctions within the target classification;
		  <em>broad</em> &ndash; tapping into a variety of semantic
		  features of the classes; and <em>inexpensive</em> &#8211;
		  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.},
  download	= {http://www.cs.toronto.edu/~joanis/Papers/JoanisStevensonJames-nle13_3-2007.pdf}
		  
}

Downloads: 0