Unsupervised learning of style-sensitive word vectors

Reina Akama, Kento Watanabe, Sho Yokoi, Sosuke Kobayashi, Kentaro Inui

研究成果: Conference contribution

抄録

This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner. We propose extending the continuous bag of words (CBOW) model (Mikolov et al., 2013a) to learn style-sensitive word vectors using a wider context window under the assumption that the style of all the words in an utterance is consistent. In addition, we introduce a novel task to predict lexical stylistic similarity and to create a benchmark dataset for this task. Our experiment with this dataset supports our assumption and demonstrates that the proposed extensions contribute to the acquisition of style-sensitive word embeddings.

本文言語English
ホスト出版物のタイトルACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
出版社Association for Computational Linguistics (ACL)
ページ572-578
ページ数7
ISBN(電子版)9781948087346
DOI
出版ステータスPublished - 2018
イベント56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
継続期間: 2018 7 152018 7 20

出版物シリーズ

名前ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
2

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
CountryAustralia
CityMelbourne
Period18/7/1518/7/20

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics

フィンガープリント 「Unsupervised learning of style-sensitive word 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