A semantic similarity measure based on lexico-syntactic patterns

Alexander Panchenko, Olga Morozova, Hubert Naets

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

22 Citations (Scopus)

Abstract

This paper presents a novel semantic similarity measure based on lexico-syntactic patterns such as those proposed by Hearst (1992). The measure achieves a correlation with human judgements up to 0.739. Additionally, we evaluate it on the tasks of semantic relation ranking and extraction. Our results show that the measure provides results comparable to the baselines without the need for any fine-grained semantic resource such as WordNet.

Original languageEnglish
Title of host publication11th Conference on Natural Language Processing, KONVENS 2012
Subtitle of host publicationEmpirical Methods in Natural Language Processing - Proceedings of the Conference on Natural Language Processing 2012
Pages174-178
Number of pages5
Publication statusPublished - 2012
Externally publishedYes
Event11th Conference on Natural Language Processing 2012: Empirical Methods in Natural Language Processing, KONVENS 2012 - Vienna, Austria
Duration: 19 Sep 201221 Sep 2012

Publication series

Name11th Conference on Natural Language Processing, KONVENS 2012: Empirical Methods in Natural Language Processing - Proceedings of the Conference on Natural Language Processing 2012
Volume5

Conference

Conference11th Conference on Natural Language Processing 2012: Empirical Methods in Natural Language Processing, KONVENS 2012
Country/TerritoryAustria
CityVienna
Period19/09/1221/09/12

Fingerprint

Dive into the research topics of 'A semantic similarity measure based on lexico-syntactic patterns'. Together they form a unique fingerprint.

Cite this