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 1909.13151cs.CL
收藏

机器翻译中的源目标域不匹配问题

The Source-Target Domain Mismatch Problem in Machine Translation

Facebook AI Research(脸书人工智能研究院)

Jiajun Shen, Peng-Jen Chen, Matt Le, Junxian He, Jiatao Gu, Myle Ott, Michael Auli, Marc'Aurelio Ranzato

摘要:

虽然我们生活在一个日益相互联系的世界中,但不同的地方仍然展现出截然不同的文化,我们在日常生活中经历的许多事件只与我们生活的特定地方有关。因此,人们经常在世界不同的地方谈论不同的事情。在这项工作中,我们研究了本地上下文在机器翻译中的作用,并假设特别是在低资源设置中,这会导致源语言和目标语言的域大大不匹配,因为这两种语言通常在世界上更遥远的地区使用,具有更独特的文化特征和不相关的本地事件。我们首先形式化的概念,源目标域不匹配,提出了一个度量来量化它,并提供实证证据证实我们的直觉,说非常不同的语言的人所产生的有机文本表现出最显着的差异。最后,我们的实证研究如何源目标域不匹配影响训练的机器翻译系统的低资源语言对。特别是,我们发现,它严重影响回翻译,但退化可以减轻回翻译与自我训练相结合,并通过增加目标侧单语数据的相对量。

英文摘要:

While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in. As a result, people often talk about different things in different parts of the world. In this work we study the effect of local context in machine translation and postulate that particularly in low resource settings this causes the domains of the source and target language to greatly mismatch, as the two languages are often spoken in further apart regions of the world with more distinctive cultural traits and unrelated local events. We first formalize the concept of source-target domain mismatch, propose a metric to quantify it, and provide empirical evidence corroborating our intuition that organic text produced by people speaking very different languages exhibits the most dramatic differences. We conclude with an empirical study of how source-target domain mismatch affects training of machine translation systems for low resource language pairs. In particular, we find that it severely affects back-translation, but the degradation can be alleviated by combining back-translation with self-training and by increasing the relative amount of target side monolingual 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。

↑