arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1902.09508cs.CLcs.LG
收藏

利用合成噪声提高机器翻译的鲁棒性

Improving Robustness of Machine Translation with Synthetic Noise

Language Technologies Institute(语言技术研究所);School of Computer Science(计算机科学学院);Carnegie Mellon University(卡内基梅隆大学)

Vaibhav Vaibhav, Sumeet Singh, Craig Stewart, Graham Neubig

摘要:

现代机器翻译(MT)系统在干净的域内文本上表现一贯良好。然而,大多数人类生成的文本,特别是在社交媒体领域,充满了错别字,俚语,方言,习语和其他噪音,这可能对输出翻译的准确性产生灾难性的影响。在本文中,我们利用机器翻译的噪声文本(MTNT)数据集,以提高机器翻译系统的鲁棒性,通过模仿自然发生的噪音,否则干净的数据。以这种方式合成噪声,我们最终能够使普通MT系统对自然发生的噪声有弹性,并部分减轻由此导致的准确性损失。

英文摘要:

Modern Machine Translation (MT) systems perform consistently well on clean, in-domain text. However most human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can have a disastrous impact on the accuracy of output translation. In this paper we leverage the Machine Translation of Noisy Text (MTNT) dataset to enhance the robustness of MT systems by emulating naturally occurring noise in otherwise clean data. Synthesizing noise in this manner we are ultimately able to make a vanilla MT system resilient to naturally occurring noise and partially mitigate loss in accuracy resulting therefrom.

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。

↑