Abstract
We empirically investigate learning from partial feedback in neural machine translation (NMT), when partial feedback is collected by asking users to highlight a correct chunk of a translation. We propose a simple and effective way of utilizing such feedback in NMT training. We demonstrate how the common machine translation problem of domain mismatch between training and deployment can be reduced solely based on chunk-level user feedback. We conduct a series of simulation experiments to test the effectiveness of the proposed method. Our results show that chunk-level feedback outperforms sentence based feedback by up to 2.61% BLEU absolute.
Abstract (translated)
我们凭经验调查了神经机器翻译(NMT)中的部分反馈学习,当部分反馈通过询问用户突出显示正确的翻译块来收集时。我们提出一种在NMT训练中利用这种反馈的简单而有效的方法。我们演示了如何根据大块级别的用户反馈来减少常见的机器翻译问题,即培训和部署之间的域不匹配问题。我们进行了一系列的模拟实验来测试所提出方法的有效性。我们的研究结果表明,大块级别的反馈优于基于句子的反馈,最高可达2.61%BLEU绝对值。
URL
https://arxiv.org/abs/1806.07169