Vector-to-sequence models for sentence analogies

Liyan Wang, Yves Lepage

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

We solve sentence analogies by generating the solution rather than identifying the best candidate from a given set of candidates, as usually done. We design a decoder to transform sentence embedding vectors back into sequences of words. To generate the vector representations of answer sentences, we build a linear regression network which learns the mapping between the distribution of known and expected vectors. We subsequently leverage this pre-trained decoder to decode sentences from regressed vectors. The results of experiments conducted on a set of semantico-formal sentence analogies show that our proposed solution performs better than a state-of-the-art baseline vector offset method which solves analogies using embeddings.

本文言語English
ホスト出版物のタイトル2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ441-446
ページ数6
ISBN(電子版)9781728192796
DOI
出版ステータスPublished - 2020 10月 17
イベント12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020 - Virtual, Depok, Indonesia
継続期間: 2020 10月 172020 10月 18

出版物シリーズ

名前2020 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020

Conference

Conference12th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2020
国/地域Indonesia
CityVirtual, Depok
Period20/10/1720/10/18

ASJC Scopus subject areas

  • コンピュータ サイエンス(その他)
  • 人工知能
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • 情報システム
  • 信号処理

フィンガープリント

「Vector-to-sequence models for sentence analogies」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