基于自我对比学习的文本转述生成研究
Ling Yuan1, Hai Ping Yu2, Junlin Ren1
1School of Computing Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, People's Republic of China.
PloS one
|September 2, 2025
概括
这项研究引入了两个自我对比的学习模型,ContraGAN和ContraMetrics,以显著提高文本转述的质量和多样性. 这些模型为各种自然语言生成应用提供实用解决方案.
科学领域:
- 自然语言生成
- 计算语言学
- 人工智能
背景情况:
- 在机器翻译和对话系统等自然语言生成 (NLG) 任务中,
- 目前的方法难以产生高质量和多样化的副词.
- 这种限制阻碍了NLG申请的有效性.
研究的目的:
- 提高文本转述的质量和多样性.
- 引入新的自我对比的学习模型,以改善对照的生成.
- 解决现有的转述生成技术的局限性.
主要方法:
- 开发了对比的生成对抗网络 (ContraGAN) 进行监督学习.
- 介绍了用于无监督学习的对比模型与指标 (ContraMetrics).
- ContraGAN使用分辨器来精制质量;ContraMetrics使用多度过和关键字提示来实现多样性.
主要成果:
- 这两种模型都比基准数据集的最新方法有了显著的改进.
- ContraGAN提高了语义准确性 (BERTScore +0. 46) 和流利性 (复杂性 - 1.57).
- 增加了多样性和词汇丰富性 (iBLEU+0.37,P-BLEU+3.34).
结论:
- 提出的自我对比的学习模式有效地解决了对外表达的关键挑战.
- 对于NLG应用,ContraGAN和ContraMetrics提供了实用和改进的解决方案.
- 这些模型有助于推进多样化和高质量的文本生成的最新技术.
更多相关视频
相关概念视频
Self-Discrepancy Theory
18.4K
One influential perspective on what motivates people's behavior is detailed in Tory Higgin's self-discrepancy theory (Higgins, 1987). He proposed that people hold disagreeing internal representations of themselves that lead to different emotional states.
18.4K
The Sense of Self: Reflected Self-Appraisal and Social Comparison
51.4K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
51.4K
Self-Presentation: Self-Monitoring and Self-Handicapping
40.2K
People can go to great lengths to protect their self-image and present themselves in ways that they want others to see them. Sociologist Erving Goffman presented the idea that a person is like an actor on a stage. Calling his theory dramaturgy, Goffman believed that we use “impression management” to present ourselves to others as we hope to be perceived. Each situation is a new scene, and individuals perform different roles depending on who is present (Goffman, 1959). Think about...
40.2K
Comparing Experimental Results: Student's t-Test
1.9K
The t-test is a statistical method used to compare the sample mean with a population mean or compare two means from two data sets. The test statistic is calculated from the standard deviation, mean, and number of measurements in the data set at a selected confidence interval and then compared to a table of critical values at this confidence level. If the test statistic is smaller than the critical value, the null hypothesis is accepted. In this case, we state that the difference between the...
1.9K
Stereotype Threat and Self-fulfilling Prophecies
38.7K
When we hold a stereotype about a person, we have expectations that he or she will fulfill that stereotype. A self-fulfilling prophecy is an expectation held by a person that alters his or her behavior in a way that tends to make it true. When we hold stereotypes about a person, we tend to treat the person according to our expectations. This treatment can influence the person to act according to our stereotypic expectations, thus confirming our stereotypic beliefs. Research by Rosenthal and...
38.7K
Self-Evaluation: Self-Enhancement and Self-Verification
5.3K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.3K


