What analogies reveal about word vectors and their compositionality

Gregory P. Finley, Stephanie Farmer, Serguei V.S. Pakhomov

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

6 Scopus citations

Abstract

Analogy completion via vector arithmetic has become a common means of demonstrating the compositionality of word embeddings. Previous work have shown that this strategy works more reliably for certain types of analogical word relationships than for others, but these studies have not offered a convincing account for why this is the case. We arrive at such an account through an experiment that targets a wide variety of analogy questions and defines a baseline condition to more accurately measure the efficacy of our system. We find that the most reliably solvable analogy categories involve either 1) the application of a morpheme with clear syntactic effects, 2) male-female alternations, or 3) named entities. These broader types do not pattern cleanly along a syntactic- semantic divide. We suggest instead that their commonality is distributional, in that the difference between the distributions of two words in any given pair encompasses a relatively small number of word types. Our study offers a needed explanation for why analogy tests succeed and fail where they do and provides nuanced insight into the relationship between word distributions and the theoretical linguistic domains of syntax and semantics.

Original languageEnglish (US)
Title of host publication*SEM 2017 - 6th Joint Conference on Lexical and Computational Semantics, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages1-11
Number of pages11
ISBN (Electronic)9781945626531
DOIs
StatePublished - 2017
Event6th Joint Conference on Lexical and Computational Semantics, *SEM 2017 - Vancouver, Canada
Duration: Aug 3 2017Aug 4 2017

Publication series

Name*SEM 2017 - 6th Joint Conference on Lexical and Computational Semantics, Proceedings

Other

Other6th Joint Conference on Lexical and Computational Semantics, *SEM 2017
CountryCanada
CityVancouver
Period8/3/178/4/17

Bibliographical note

Funding Information:
This work was partially supported by a University of Minnesota Academic Health Center Faculty Development Award and by the National Institute of General Medical Sciences (GM102282).

Fingerprint Dive into the research topics of 'What analogies reveal about word vectors and their compositionality'. Together they form a unique fingerprint.

Cite this