Vector Similarity of Related Words in the Japanese Word Net

Takuya Hirao, Nao Wariishi, Takahiko Suzuki, Sachio Hirokawa

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

    Abstract

    Word2vec is a tool that produces vector representation of words from a large amount of text data. In this paper, we show that only a part of the vector space produced by word2vec is enough to represent the collective sense of a set of related words in the Japanese Word Net. Further, we will show that there is a subspace in the vector space which do not relate to the collective sense. We construct a compact decision tree by using the vectors in order to distinguish whether a given word belongs to the set of related words.

    Original languageEnglish
    Title of host publicationProceedings - 2015 IIAI 4th International Congress on Advanced Applied Informatics, IIAI-AAI 2015
    EditorsSachio Hirokawa, Kiyota Hashimoto, Tokuro Matsuo, Tsunenori Mine
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages142-147
    Number of pages6
    ISBN (Electronic)9781479999583
    DOIs
    Publication statusPublished - Jan 6 2016
    Event4th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2015 - Okayama, Japan
    Duration: Jul 12 2015Jul 16 2015

    Publication series

    NameProceedings - 2015 IIAI 4th International Congress on Advanced Applied Informatics, IIAI-AAI 2015

    Other

    Other4th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2015
    Country/TerritoryJapan
    CityOkayama
    Period7/12/157/16/15

    All Science Journal Classification (ASJC) codes

    • Information Systems
    • Computer Networks and Communications
    • Computer Science Applications
    • Computer Vision and Pattern Recognition

    Fingerprint

    Dive into the research topics of 'Vector Similarity of Related Words in the Japanese Word Net'. Together they form a unique fingerprint.

    Cite this