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

Anna Rogers, Aleksandr Drozd, Bofang Li

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer 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.
    OriginalsprogEngelsk
    TitelProceedings of the 6th Joint Conference on Lexical and Computational Semantics (* SEM 2017)
    Antal sider14
    Publikationsdato2017
    Sider135-148
    StatusUdgivet - 2017

    Emneord

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

    Fingeraftryk

    Dyk ned i forskningsemnerne om 'The (Too Many) Problems of Analogical Reasoning with Word Vectors'. Sammen danner de et unikt fingeraftryk.

    Citationsformater