arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.04578cs.CL
收藏

SC2:增强长文本风格迁移中的内容保留与风格一致性

SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer

School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院)

Jie Zhao, Ziyu Guan, Cai Xu, Wei Zhao, Yue Jiang

AI总结:

本文提出SC2方法,通过多层联合风格-内容加权模块和风格一致性损失解决长文本风格迁移中的内容退化和风格不一致问题,并引入去噪非自回归解码器加速训练,实验表明其优于竞争基线。

摘要:

文本风格迁移(TST)旨在改变文本的风格极性,同时保留语义内容。尽管近期进展在短文本TST中表现出显著成效,但该任务仍相对简单,实际应用有限。更全面的长文本TST任务面临两个挑战:(1)现有方法难以准确评估多个词中的内容属性,导致内容退化;(2)传统的普通风格分类器损失在多个生成句子之间保持一致风格方面遇到障碍。本文提出了一种新方法SC2,其中设计了多层联合风格-内容加权(JSCW)模块和风格一致性损失来解决这两个问题。JSCW同时评估一个token中风格和内容属性的数量,旨在获得无损内容表示,从而增强内容保留。多个JSCW层进一步逐步细化内容表示。我们设计了风格一致性损失,以确保生成的多个句子一致地反映目标风格极性。此外,我们引入了一个去噪非自回归解码器以加速训练。我们进行了大量实验,结果表明SC2相较于竞争基线有显著改进。我们的代码:https://github.com/jiezhao6/SC2。

英文摘要:

Text style transfer (TST) aims to vary the style polarity of text while preserving the semantic content. Although recent advancements have demonstrated remarkable progress in short TST, it remains a relatively straightforward task with limited practical applications. The more comprehensive long TST task presents two challenges: (1) existing methods encounter difficulties in accurately evaluating content attributes in multiple words, leading to content degradation; (2) the conventional vanilla style classifier loss encounters obstacles in maintaining consistent style across multiple generated sentences. In this paper, we propose a novel method SC2, where a multilayer Joint Style-Content Weighed (JSCW) module and a Style Consistency loss are designed to address the two issues. The JSCW simultaneously assesses the amounts of style and content attributes within a token, aiming to acquire a lossless content representation and thereby enhancing content preservation. The multiple JSCW layers further progressively refine content representations. We design a style consistency loss to ensure the generated multiple sentences consistently reflect the target style polarity. Moreover, we incorporate a denoising non-autoregressive decoder to accelerate the training. We conduct plentiful experiments and the results show significant improvements of SC2 over competitive baselines. Our code: https://github.com/jiezhao6/SC2.

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。

↑