FIRE: Semantic Field of Words Represented as Nonlinear Functions

研究成果: Conference contribution

抄録

State-of-the-art word embeddings presume a linear vector space, but this approach does not easily incorporate the nonlinearity that is necessary to represent polysemy. We thus propose a novel semantic FIeld REepresentation, called FIRE, which is a D-dimensional field in which every word is represented as a set of its locations and a nonlinear function covering the field. The strength of a word* relation to another word at a certain location is measured as the function value at that location. With FIRE, compositionality is represented via functional additivity, whereas polysemy is represented via the set of points and the function* multimodality. By implementing FIRE for English and comparing it with previous representation methods via word and sentence similarity tasks, we show that FIRE produces comparable or even better results. In an evaluation of polysemy to predict the number of word senses, FIRE greatly outperformed BERT and Word2vec, providing evidence of how FIRE represents polysemy. The code is available at https://github.com/kduxin/firelang.

本文言語English
ホスト出版物のタイトルAdvances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
編集者S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
出版社Neural information processing systems foundation
ISBN(電子版)9781713871088
出版ステータスPublished - 2022
外部発表はい
イベント36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans, United States
継続期間: 2022 11月 282022 12月 9

出版物シリーズ

名前Advances in Neural Information Processing Systems
35
ISSN(印刷版)1049-5258

Conference

Conference36th Conference on Neural Information Processing Systems, NeurIPS 2022
国/地域United States
CityNew Orleans
Period22/11/2822/12/9

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • 情報システム
  • 信号処理

フィンガープリント

「FIRE: Semantic Field of Words Represented as Nonlinear Functions」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