Leveraging preposition ambiguity to assess compositional distributional models of semantics

Samuel Ritter, Cotie Long, Denis Paperno, Marco Baroni, Matthew Botvinick, Adele Goldberg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Complex interactions among the meanings of words are important factors in the function that maps word meanings to phrase meanings. Recently, compositional distributional semantics models (CDSM) have been designed with the goal of emulating these complex interactions; however, experimental results on the effectiveness of CDSM have been difficult to interpret because the current metrics for assessing them do not control for the confound of lexical information. We present a new method for assessing the degree to which CDSM capture semantic interactions that dissociates the influences of lexical and compositional information. We then provide a dataset for performing this type of assessment and use it to evaluate six compositional models using both co-occurrence based and neural language model input vectors. Results show that neural language input vectors are consistently superior to co-occurrence based vectors, that several CDSM capture substantial compositional information, and that, surprisingly, vector addition matches and is in many cases superior to purpose-built paramaterized models.

Original languageEnglish (US)
Title of host publicationProceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
PublisherAssociation for Computational Linguistics (ACL)
Pages199-204
Number of pages6
ISBN (Electronic)9781941643396
StatePublished - Jan 1 2015
Event4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 - Denver, United States
Duration: Jun 4 2015Jun 5 2015

Publication series

NameProceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015

Other

Other4th Joint Conference on Lexical and Computational Semantics, *SEM 2015
CountryUnited States
CityDenver
Period6/4/156/5/15

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Leveraging preposition ambiguity to assess compositional distributional models of semantics'. Together they form a unique fingerprint.

  • Cite this

    Ritter, S., Long, C., Paperno, D., Baroni, M., Botvinick, M., & Goldberg, A. (2015). Leveraging preposition ambiguity to assess compositional distributional models of semantics. In Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015 (pp. 199-204). (Proceedings of the 4th Joint Conference on Lexical and Computational Semantics, *SEM 2015). Association for Computational Linguistics (ACL).