How well do distributional models capture different types of semantic knowledge?

Dana Rubinstein, Effi Levi, Roy Schwartz, Ari Rappoport

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

57 Scopus citations

Abstract

In recent years, distributional models (DMs) have shown great success in representing lexical semantics. In this work we show that the extent to which DMs represent semantic knowledge is highly dependent on the type of knowledge. We pose the task of predicting properties of concrete nouns in a supervised setting, and compare between learning taxonomic properties (e.g., animacy) and attributive properties (e.g., size, color). We employ four state-of-the-art DMs as sources of feature representation for this task, and show that they all yield poor results when tested on attributive properties, achieving no more than an average F-score of 0.37 in the binary property prediction task, compared to 0.73 on taxonomic properties. Our results suggest that the distributional hypothesis may not be equally applicable to all types of semantic information.

Original languageAmerican English
Title of host publicationACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages726-730
Number of pages5
ISBN (Electronic)9781941643730
DOIs
StatePublished - 2015
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: 26 Jul 201531 Jul 2015

Publication series

NameACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
Volume2

Conference

Conference53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
Country/TerritoryChina
CityBeijing
Period26/07/1531/07/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'How well do distributional models capture different types of semantic knowledge?'. Together they form a unique fingerprint.

Cite this