arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.16189cs.CL
收藏

翻译过程中的自动纠错--多任务学习提高对话式机器翻译

Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation

ByteDance AI Lab(字节跳动人工智能实验室);School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部)

Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei Li, Deyi Xiong

摘要:

对话文本的自动翻译是许多现实生活场景中非常需要的需求。然而,目前现有的神经机器翻译提供不令人满意的结果。本文通过对一个对话语料库的深入分析,总结了对话翻译中的三个主要问题:代词省略(\droppro)、标点省略(\droppun)和错别字(\typo)。针对这些挑战,我们提出了一种联合学习方法来识别遗漏和错别字,并利用上下文来翻译对话话语。为了正确评估性能,我们提出了一个人工标注的数据集,其中包含来自300个对话的1,931个汉英平行话语作为对话翻译的基准测试平台。我们的实验表明,所提出的方法提高了3.2 BLEU的基线翻译质量。省略代词的回收率也从26.09%提高到47.16%。我们将在https://github.com/rgwt123/DialogueMT上公开发布代码和数据集。

英文摘要:

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue corpus and summarize three major issues on dialogue translation, including pronoun dropping (\droppro), punctuation dropping (\droppun), and typos (\typo). In response to these challenges, we propose a joint learning method to identify omission and typo, and utilize context to translate dialogue utterances. To properly evaluate the performance, we propose a manually annotated dataset with 1,931 Chinese-English parallel utterances from 300 dialogues as a benchmark testbed for dialogue translation. Our experiments show that the proposed method improves translation quality by 3.2 BLEU over the baselines. It also elevates the recovery rate of omitted pronouns from 26.09% to 47.16%. We will publish the code and dataset publicly at https://github.com/rgwt123/DialogueMT.

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。

↑