| 摘要: |
| 文本风格迁移是近年来自然语言处理领域的热点问题之一，旨在保留文本内容的基础上通过编辑或生成的方式更改文本的特定风格或属性（如情感、时态和性别等）.旨在梳理已有的技术，以推进该方向的研究.首先，给出文本风格迁移问题的定义及其面临的挑战；然后，对已有方法进行分类综述，重点介绍基于无监督学习的文本风格迁移方法并将其进一步分为隐式和显式两类方法，对各类方法在实现机制、优势、局限性和性能等方面进行分析和比较；同时，还通过实验比较了几种代表性方法在风格迁移准确率、文本内容保留和困惑度等自动化评价指标上的性能；最后，对文本风格迁移研究进行总结和展望. |
| 关键词: 文本风格迁移 自然语言处理 对抗学习 强化学习 机器翻译 |
| DOI：10.13328/j.cnki.jos.006544 |
| 分类号: |
| 基金项目:国家自然科学基金（61772284，61876091） |
|
| Survey on Text Style Transfer Research |
|
CHEN Ke-Jia1,2, FEI Zi-Yang1, CHEN Jing-Qiang1,2, YANG Zi-Nong1
|
|
1.School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China;2.Jiangsu Key Laboratory of Big Data Security & Intelligent Processing (Nanjing University of Posts and Telecommunications), Nanjing 210023, China
|
| Abstract: |
| Text style transfer is one of the hot issues in the field of natural language processing in recent years. It aims to transfer the specific style or attributes of the text (such as emotion, tense, gender, etc.) through editing or generating while retaining the text content. The purpose of this study is to sort out the existing methods in order to advance this research field. First, the problem of text style transfer is defined and the challenges are given. Then, the existing methods are classified and reviewed, focusing on the TST methods based on unsupervised learning and further dividing them into the implicit methods and the explicit methods. The implementation mechanisms, advantages, limitations, and performance of each method are also analyzed. Subsequently, the performance of several representative methods on automatic evaluation indicators such as transfer accuracy, text content retention, and perplexity are compared through experiments. Finally, the research of text style transfer is concluded and prospected. |
| Key words: text style transfer (TST) natural language processing adversarial learning reinforcement learning machine translation |
