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.
翻译:最先进的机器翻译模型仍然不如翻译人。 先前的工作将人际互动引入神经机翻译流程,以获得目标语言的改进结果。 但是,并非所有的模型翻译错误都相等 -- -- 有些是关键错误,而另一些则是次要的。 与此同时,同样的翻译错误也反复发生。 为了解决这两个问题,我们提议CAMIT, 这是一种在互动环境中翻译的新颖方法。 我们建议的方法与关键修订指令一起工作, 因此, 我们建议的方法允许人纠正在翻译模型的句子中的任意词句。 此外, CAMIT还学习了基于背景的修改行动, 并温柔地回忆了这些修改行动, 减轻了重复错误的问题。 理想和真实互动翻译环境的实验表明, 我们提议的\ 方法可以大大增强机器翻译结果,同时比以往的方法少要求人类的修改指令 。