arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04512cs.CLcs.LG
收藏

基于机器翻译的面向任务的NLG输出本地化

Using Machine Translation to Localize Task Oriented NLG Output

Google, Inc.(谷歌公司)

Scott Roy, Cliff Brunk, Kyu-Young Kim, Justin Zhao, Markus Freitag, Mihir Kale, Gagan Bansal, Sidharth Mudgal, Chris Varano

摘要:

面向任务的自然语言应用程序(如Google Assistant,Siri或Alexa)的挑战之一是将输出本地化为多种语言。本文通过将机器翻译应用到英语输出中来探索这一点。使用机器翻译是非常可扩展的,因为它可以与任何英语输出,并可以处理动态文本,但除此之外的问题是一个穷人的适合。所需的质量棒接近完美,句子的范围极窄,而且句子往往与机器翻译训练数据中的句子有很大不同。这种需求的组合在机器翻译的领域自适应领域中是新颖的。我们能够通过建立现有的想法并添加新的想法来达到所需的质量标准:对域内翻译进行微调,添加来自Web的句子,添加语义注释以及使用自动错误检测。本文分享了我们的方法和结果,以及一个蒸馏模型,以服务于大规模的翻译模型。

英文摘要:

One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English output. Using machine translation is very scalable, as it can work with any English output and can handle dynamic text, but otherwise the problem is a poor fit. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different than the ones in the machine translation training data. This combination of requirements is novel in the field of domain adaptation for machine translation. We are able to reach the required quality bar by building on existing ideas and adding new ones: finetuning on in-domain translations, adding sentences from the Web, adding semantic annotations, and using automatic error detection. The paper shares our approach and results, together with a distillation model to serve the translation models at scale.

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。

↑