Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info


New from Oxford University Press!

ad

Cognitive Literary Science

Edited by Michael Burke and Emily T. Troscianko

Cognitive Literary Science "Brings together researchers in cognitive-scientific fields and with literary backgrounds for a comprehensive look at cognition and literature."


New from Cambridge University Press!

ad

Intonation and Prosodic Structure

By Caroline Féry

Intonation and Prosodic Structure "provides a state-of-the-art survey of intonation and prosodic structure."


Academic Paper


Title: A general feature space for automatic verb classification
Author: Eric Joanis
Institution: University of Toronto
Author: Suzanne Stevenson
Institution: University of Toronto
Author: David James
Institution: University of Toronto
Linguistic Field: Computational Linguistics; Semantics
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 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.

CUP AT LINGUIST

This article appears IN Natural Language Engineering Vol. 14, Issue 3.

Return to TOC.

Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page