Learning semantically and additively compositional distributional representations

Ran Tian, Naoaki Okazaki, Kentaro Inui

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

5 Citations (Scopus)

Abstract

This paper connects a vector-based composition model to a formal semantics, the Dependency-based Compositional Semantics (DCS). We show theoretical evidence that the vector compositions in our model conform to the logic of DCS. Experimentally, we show that vector-based composition brings a strong ability to calculate similar phrases as similar vectors, achieving near state-of-the-art on a wide range of phrase similarity tasks and relation classification; meanwhile, DCS can guide building vectors for structured queries that can be directly executed. We evaluate this utility on sentence completion task and report a new state-of-the-art.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages1277-1287
Number of pages11
ISBN (Electronic)9781510827585
DOIs
Publication statusPublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 2016 Aug 72016 Aug 12

Publication series

Name54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Volume3

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period16/8/716/8/12

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint Dive into the research topics of 'Learning semantically and additively compositional distributional representations'. Together they form a unique fingerprint.

Cite this