This paper shows that standard assessment methodology for style transfer has several significant problems. First, the standard metrics for style accuracy and semantics preservation vary significantly on different re-runs. Therefore one has to report error margins for the obtained results. Second, starting with certain values of bilingual evaluation understudy (BLEU) between input and output and accuracy of the sentiment transfer the optimization of these two standard metrics diverge from the intuitive goal of the style transfer task. Finally, due to the nature of the task itself, there is a specific dependence between these two metrics that could be easily manipulated. Under these circumstances, we suggest taking BLEU between input and human-written reformulations into consideration for benchmarks. We also propose three new architectures that outperform state of the art in terms of this metric.
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
College of Engineering and Computer Science, Marshall University（马歇尔大学工程与计算机科学学院）；Department of Computer Science and Engineering, University of Rajshahi（拉贾沙希大学计算机科学与工程系）；Miami University（迈阿密大学）
Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings
Google Research（谷歌研究院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
风格转换是将句子改写成目标风格，同时大致保留内容的任务。虽然大多数先前的文献假设访问大型风格标记语料库，但最近的工作（Riley et al. 2021）尝试了“Few-Shot”风格迁移，仅使用3-10个句子进行风格提取的推理。在这项工作中，我们研究了一个相关的低资源设置：没有风格标记语料库的语言的风格转移。我们注意到，现有的Few-Shot方法执行此任务很差，通常逐字复制输入。我们推动了Few-Shot风格转换的最新技术，提出了一种新的方法来模拟释义之间的风格差异。与以前的工作相比，我们的模型在七种语言的正式传输和代码混合添加方面的性能提高了2- 3倍。此外，我们的方法是更好地控制风格转移幅度使用输入标量旋钮。我们报告了几个属性转移任务（情感转移，简化，性别中立化，文本匿名化）的有希望的定性结果，所有这些都没有重新训练模型。最后，我们发现模型评估是困难的，由于缺乏数据集和许多语言的指标。为了方便未来的研究，我们众包正式注释4000句对四种印度语言，并使用这些数据来设计我们的自动评估。
Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics
Department of Computer Science, Aarhus University, Denmark（计算机科学系，奥胡斯大学）；Department of Computer Science, University of Copenhagen, Denmark（计算机科学系，哥本哈根大学）
Back-Translation-Style Data Augmentation for End-to-End ASR
Nagoya University（名古屋大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Google, Inc.（谷歌公司）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））；INESC-ID Lisboa（里斯本信息与通信技术研究院 - 数字系统工程研究所）
