arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00469cs.CLcs.AI
收藏

基于对比学习的文本风格迁移

Gradient-guided Unsupervised Text Style Transfer via Contrastive Learning

School of Computer Science, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院)

Chenghao Fan, Ziao Li, Wei wei

摘要:

文本风格转换是一个具有挑战性的文本生成问题,其目的是在保持句子内容不变的情况下,将给定句子的风格转换为目标句子的风格。由于并行数据集的自然稀缺性,最近的工作主要集中在以无监督的方式解决问题。然而,以前的基于梯度的工作普遍遭受以下不足,即:(1)内容迁移。以前的方法缺乏明确的内容不变性的模型,因此容易受到内容转移之间的原始句子和转移。(2)风格分类错误。梯度引导方法的一个自然缺点是推理过程与对抗攻击是同质的,使得潜在的优化容易由于误分类而成为对分类器的攻击。这导致难以实现高转印精度。为了解决这些问题,我们提出了一种新的梯度引导模型,通过文本风格转移的对比范式,明确收集相似的语义句子,并设计了一个基于连体结构的风格分类器,以缓解这两个问题,分别。两个数据集上的实验表明,我们提出的方法的有效性,相比,国家的最先进的。

英文摘要:

Text style transfer is a challenging text generation problem, which aims at altering the style of a given sentence to a target one while keeping its content unchanged. Since there is a natural scarcity of parallel datasets, recent works mainly focus on solving the problem in an unsupervised manner. However, previous gradient-based works generally suffer from the deficiencies as follows, namely: (1) Content migration. Previous approaches lack explicit modeling of content invariance and are thus susceptible to content shift between the original sentence and the transferred one. (2) Style misclassification. A natural drawback of the gradient-guided approaches is that the inference process is homogeneous with a line of adversarial attack, making latent optimization easily becomes an attack to the classifier due to misclassification. This leads to difficulties in achieving high transfer accuracy. To address the problems, we propose a novel gradient-guided model through a contrastive paradigm for text style transfer, to explicitly gather similar semantic sentences, and to design a siamese-structure based style classifier for alleviating such two issues, respectively. Experiments on two datasets show the effectiveness of our proposed approach, as compared to the state-of-the-arts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑