论文标题
半监督的形式风格转移和一致性培训
Semi-Supervised Formality Style Transfer with Consistency Training
论文作者
论文摘要
形式样式转移（FST）是一项任务，涉及将非正式句子解释为正式句子而不改变其含义。为了解决现有并行数据集的数据划分问题，以前的研究倾向于采用周期重建方案来利用其他未标记的数据，其中FST模型主要受益于目标侧未标记的句子。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培训的源端未标记的句子。具体而言，我们的方法通过强制执行模型为其扰动版本生成相似的输出，从而增加了从源端非正式句子获得的伪并行数据。此外，我们经验研究了各种数据扰动方法的效果，并提出了有效的数据过滤策略以改善我们的框架。 GYAFC基准测试的实验结果表明，即使有不到40％的并行数据，我们的方法也可以实现最新的结果。
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.
