Sentence-level Revision with Neural Reinforcement Learning

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

The objective of Sentence-level Revision (SentRev) is to enhance the fluency of English writing; however, the performance of the three baseline methods is notably suboptimal. In this study, we propose a method utilizing neural reinforcement learning, tailored to the specific characteristics of this task, which has resulted in superior performance over the baseline methods, surpassing them in multiple evaluation metrics. Moreover, we have identified conspicuous bottlenecks in SentRev's efficacy in improving the fluency of English writing.

本文言語English
ホスト出版物のタイトルROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing
編集者Jheng-Long Wu, Ming-Hsiang Su, Hen-Hsen Huang, Yu Tsao, Hou-Chiang Tseng, Chia-Hui Chang, Lung-Hao Lee, Yuan-Fu Liao, Wei-Yun Ma
出版社The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
ページ202-209
ページ数8
ISBN(電子版)9789869576963
出版ステータスPublished - 2023
イベント35th Conference on Computational Linguistics and Speech Processing, ROCLING 2023 - Taipei City, Taiwan, Province of China
継続期間: 2023 10月 202023 10月 21

出版物シリーズ

名前ROCLING 2023 - Proceedings of the 35th Conference on Computational Linguistics and Speech Processing

Conference

Conference35th Conference on Computational Linguistics and Speech Processing, ROCLING 2023
国/地域Taiwan, Province of China
CityTaipei City
Period23/10/2023/10/21

ASJC Scopus subject areas

  • 言語および言語学
  • 言語聴覚療法

フィンガープリント

「Sentence-level Revision with Neural Reinforcement Learning」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