The (Too Many) Problems of Analogical Reasoning with Word Vectors

Anna Rogers, Aleksandr Drozd, Bofang Li

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

    Abstract

    This paper explores the possibilities of analogical reasoning with vector space models. Given two pairs of words with the same relation (e.g. man:woman :: king:queen), it was proposed that the offset between one pair of the corresponding word vectors can be used to identify the unknown member of the other pair (king - man + woman = queen). We argue against such “linguistic regularities” as a model for linguistic relations in vector space models and as a benchmark, and we show that the vector offset (as well as two other, better-performing methods) suffers from dependence on vector similarity.
    Original languageEnglish
    Title of host publicationProceedings of the 6th Joint Conference on Lexical and Computational Semantics (* SEM 2017)
    Number of pages14
    Publication date2017
    Pages135-148
    Publication statusPublished - 2017

    Keywords

    • Analogical Reasoning
    • Vector Space Models
    • Linguistic Relations
    • Word Vectors
    • Vector Similarity

    Fingerprint

    Dive into the research topics of 'The (Too Many) Problems of Analogical Reasoning with Word Vectors'. Together they form a unique fingerprint.

    Cite this