更正和翻译：从交互式修订中学习翻译
Correct-and-Memorize: Learning to Translate from Interactive Revisions
摘要：
最先进的机器翻译模型仍然无法与人工翻译相提并论。先前的工作将人类交互引入神经机器翻译过程，以获得目标语言的改进结果。然而，并不是所有的模型转换错误都是相等的-有些是关键的，而另一些是次要的。同时，同样的翻译错误在相似的语境中反复出现。为了解决这两个问题，我们提出了CAMIT，一种新的方法，在一个互动的环境中进行翻译。我们所提出的方法与关键的修订指令，因此允许人类纠正模型翻译的句子中的任意单词。此外，CAMIT根据上下文学习并软记忆修改操作，减轻重复错误的问题。在理想和真实的交互式翻译环境中的实验表明，我们提出的\method增强机器翻译的结果显着，同时需要更少的修订指令从人类相比，以前的方法。
英文摘要：
State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all model-translation errors are equal -- some are critical while others are minor. In the meanwhile, the same translation mistakes occur repeatedly in a similar context. To solve both issues, we propose CAMIT, a novel method for translating in an interactive environment. Our proposed method works with critical revision instructions, therefore allows human to correct arbitrary words in model-translated sentences. In addition, CAMIT learns from and softly memorizes revision actions based on the context, alleviating the issue of repeating mistakes. Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods.
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。
