跳到主要导航 跳到搜索 跳到主要内容

CTG:A Controllable Text Generation Method based on the Joint Work of Language Model and Text Classifier

  • Xuyuan Liang
  • , Lihua Tian
  • , Chen Li
  • , Zhang Mandi
  • Xi'an Jiaotong University
  • Beijing Jiaotong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

5 引用 (Scopus)

摘要

Text generation is an important research field in natural language processing. Today pre-trained models can generate text with high readability and fluency. However, the generated text content is usually not restricted, and the generated content cannot be controlled. Therefore, there is an urgent need for a controllable text generation method. Traditional controllable text generation methods usually have the disadvantages of high training cost and difficulty in adjustment. We propose a lightweight and easy-to-adjust method to update the language model through the discrimination results of the text classification model on the language model, thereby completing controllable text generation. And we have solved the problem of imbalance and quality degradation in text generation. Experiments show that the quality of the text generated by this method can also reach a higher level with strong subjectivity, can achieves the purpose of controlling text generation. And this method is easy to adjust, suitable for various scenarios.

源语言英语
主期刊名2021 IEEE 3rd International Conference on Communications, Information System and Computer Engineering, CISCE 2021
出版商Institute of Electrical and Electronics Engineers Inc.
页817-820
页数4
ISBN(电子版)9780738112152
DOI
出版状态已出版 - 14 5月 2021
活动3rd IEEE International Conference on Communications, Information System and Computer Engineering, CISCE 2021 - Beijing, 中国
期限: 14 5月 2021 → 16 5月 2021

丛书

姓名2021 IEEE 3rd International Conference on Communications, Information System and Computer Engineering, CISCE 2021

会议

会议3rd IEEE International Conference on Communications, Information System and Computer Engineering, CISCE 2021
国家/地区中国
市Beijing
时期14/05/21 → 16/05/21

学术指纹

探究 'CTG:A Controllable Text Generation Method based on the Joint Work of Language Model and Text Classifier' 的科研主题。它们共同构成独一无二的学术指纹。

引用此