A unified learning framework of skip-grams and global vectors

Jun Suzuki, Masaaki Nagata

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

Log-bilinear language models such as SkipGram and GloVe have been proven to capture high quality syntactic and seman-tic relationships between words in a vector space. We revisit the relationship between SkipGram and GloVe models from a ma-chine learning viewpoint, and show that these two methods are easily merged into a unified form. Then, by using the unified form, we extract the factors of the config-urations that they use differently. We also empirically investigate which factor is re-sponsible for the performance difference often observed in widely examined word similarity and analogy tasks.

本文言語English
ホスト出版物のタイトルACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
出版社Association for Computational Linguistics (ACL)
ページ186-191
ページ数6
ISBN(電子版)9781941643730
DOI
出版ステータスPublished - 2015
外部発表はい
イベント53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
継続期間: 2015 7月 262015 7月 31

出版物シリーズ

名前ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
2

Other

Other53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
国/地域China
CityBeijing
Period15/7/2615/7/31

ASJC Scopus subject areas

  • 人工知能
  • ソフトウェア
  • 言語および言語学
  • 言語学および言語

フィンガープリント

「A unified learning framework of skip-grams and global vectors」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル