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 2203.13620cs.CL
收藏

半监督形式风格迁移与一致性训练

Semi-Supervised Formality Style Transfer with Consistency Training

Tokyo Institute of Technology(东京工业大学)

Ao Liu, An Wang, Naoaki Okazaki

摘要:

正式风格转换是指在不改变句子意义的前提下,将非正式句子改写为正式句子。为了解决现有并行数据集的数据稀缺问题,以前的研究倾向于采用循环重构方案来利用额外的未标记数据,其中FST模型主要受益于目标端未标记句子。在这项工作中,我们提出了一个简单而有效的半监督框架,以更好地利用基于一致性训练的源端未标记句子。具体来说,我们的方法通过强制模型为其扰动版本生成类似的输出来增强从源端非正式句子获得的伪并行数据。此外,我们还实证研究了各种数据扰动方法的影响,并提出了有效的数据过滤策略来改进我们的框架。GYAFC基准测试的实验结果表明,我们的方法可以达到国家的最先进的结果,即使不到40%的并行数据。

英文摘要:

Formality style transfer (FST) is a task that involves paraphrasing an informal sentence into a formal one without altering its meaning. To address the data-scarcity problem of existing parallel datasets, previous studies tend to adopt a cycle-reconstruction scheme to utilize additional unlabeled data, where the FST model mainly benefits from target-side unlabeled sentences. In this work, we propose a simple yet effective semi-supervised framework to better utilize source-side unlabeled sentences based on consistency training. Specifically, our approach augments pseudo-parallel data obtained from a source-side informal sentence by enforcing the model to generate similar outputs for its perturbed version. Moreover, we empirically examined the effects of various data perturbation methods and propose effective data filtering strategies to improve our framework. Experimental results on the GYAFC benchmark demonstrate that our approach can achieve state-of-the-art results, even with less than 40% of the parallel data.

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。

↑