Home > Research > Publications & Outputs > Measuring MWE compositionality using semantic a...

Electronic data

  • W06-1202

    Final published version, 249 KB, PDF-document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Measuring MWE compositionality using semantic annotation

Research output: Contribution in Book/Report/ProceedingsPaper

Published
Publication date07/2006
Host publicationMWE '06 Proceedings of the Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties
Place of PublicationStroudsburg
PublisherAssociation for Computational Linguistics
Pages2-11
Number of pages10
ISBN (Print)1932432841
<mark>Original language</mark>English

Conference

ConferenceCOLING/ACL workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties
CitySydney, Australia
Period23/07/06 → …

Conference

ConferenceCOLING/ACL workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties
CitySydney, Australia
Period23/07/06 → …

Abstract

This paper reports on an experiment in which we explore a new approach to the automatic measurement of multi-word expression (MWE) compositionality. We propose an algorithm which ranks MWEs by their compositionality relative to a semantic field taxonomy based on the Lancaster English semantic lexicon (Piao et al., 2005a). The semantic information provided by the lexicon is used for measuring the semantic distance between a MWE and its constituent words. The algorithm is evaluated both on 89 manually ranked MWEs and on McCarthy et al's (2003) manually ranked phrasal verbs. We compared the output of our tool with human judgments using Spearman's rank-order correlation coefficient. Our evaluation shows that the automatic ranking of the majority of our test data (86.52%) has strong to moderate correlation with the manual ranking while wide discrepancy is found for a small number of MWEs. Our algorithm also obtained a correlation of 0.3544 with manual ranking on McCarthy et al's test data, which is comparable or better than most of the measures they tested. This experiment demonstrates that a semantic lexicon can assist in MWE compositionality measurement in addition to statistical algorithms.