An empirical model of multiword expression decomposability

Baldwin, Timothy, Bannard, Colin, Tanaka, Takaaki and Widdows, Dominic (2003) An empirical model of multiword expression decomposability In: Proceedings of the ACL 2003 workshop on Multiword expressions analysis, acquisition and treatment -, 2003-7-12 - 2003-7-12, Sapporo, Japan.

Access the full-text of this item by clicking on the Open Access link.

Abstract

This paper presents a construction-inspecific model of multiword expression decomposability based on latent semantic analysis. We use latent semantic analysis to determine the similarity between a multiword expression and its constituent words, and claim that higher similarities indicate greater decomposability. We test the model over English noun-noun compounds and verb-particles, and evaluate its correlation with similarities and hyponymy values in WordNet. Based on mean hyponymy over partitions of data ranked on similarity, we furnish evidence for the calculated similarities being correlated with the semantic relational content of WordNet.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	46 Information and Computing Sciences, 47 Language, Communication and Culture, 4704 Linguistics
Depositing User:	Symplectic Admin
Date Deposited:	21 Jun 2016 10:12
Last Modified:	23 May 2026 00:06
DOI:	10.3115/1119282.1119294
Open Access URL:	http://anthology.aclweb.org/W/W03/W03-1812.pdf
Related Websites:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3001735
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.