Skip to main navigation Skip to search Skip to main content

Measuring thematic fit with distributional feature overlap

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

In this paper, we introduce a new distributional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototypical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-the-art system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verb-specific semantic roles.

Original languageEnglish
Title of host publicationProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
EditorsMartha Palmer, Rebecca Hwa, Sebastian Riedel
PublisherAssociation for Computational Linguistics (ACL)
Pages648-658
Number of pages11
ISBN (Electronic)9781945626838
DOIs
Publication statusPublished - Sept 2017
Externally publishedYes
Event2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 - Copenhagen, Denmark
Duration: 9 Sept 201711 Sept 2017

Publication series

NameEMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Country/TerritoryDenmark
CityCopenhagen
Period9/09/1711/09/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Measuring thematic fit with distributional feature overlap'. Together they form a unique fingerprint.

Cite this