Testing APSyn against vector cosine on similarity estimation

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, Chu-ren Huang, Philippe Blache

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

7 Citations (Scopus)

Abstract

In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings. The recent lit ENGLerature has proposed other methods which attempt to mitigate such biases. In this paper, we intend to investigate APSyn, a measure that computes the extent of the intersection between the most associated contexts of two target words, weighting it by context relevance. We evaluated this metric in a similarity estimation task on several popular test sets, and our results show that APSyn is in fact highly competitive, even with respect to the results reported in the lit ENGLerature for word embeddings. On top of it, APSyn addresses some of the weaknesses of Vector Cosine, performing well also on genuine similarity estimation.
Original languageEnglish
Title of host publicationProceedings of the 30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016
PublisherInstitute for the Study of Language and Information
Pages229-238
Number of pages10
ISBN (Electronic)9788968174285
Publication statusPublished - 1 Jan 2016
Event30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016 - Kyung Hee University, Seoul, Korea, Republic of
Duration: 28 Oct 201630 Oct 2016

Conference

Conference30th Pacific Asia Conference on Language, Information and Computation, PACLIC 2016
CountryKorea, Republic of
CitySeoul
Period28/10/1630/10/16

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)
  • Information Systems

Cite this