论文标题
适应非中心语言的零击多语言翻译
Adapting to Non-Centered Languages for Zero-shot Multilingual Translation
论文作者
论文摘要
多语言神经机器翻译可以在训练期间翻译看不见的语言对，即零射击翻译。但是，零拍的翻译总是不稳定的。尽管先前的作品将不稳定归因于中心语言的统治，例如英语，我们以非中心语言的严格依赖性来补充这种观点。在这项工作中，我们提出了一种简单，轻巧但有效的语言特定建模方法，通过适应非中心语言，结合共享信息和特定语言的信息，以抵消零拍的不稳定。在IWSLT17，Europarl，TED Talks和Opus-100数据集上进行变压器的实验表明，我们的方法不仅在中心数据条件下的性能优于强基础，而且还可以轻松拟合非中心数据条件。通过进一步研究层归因，我们表明我们所提出的方法可以将耦合表示形式朝正确的方向拆开。
Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the domination of central language, e.g. English, we supplement this viewpoint with the strict dependence of non-centered languages. In this work, we propose a simple, lightweight yet effective language-specific modeling method by adapting to non-centered languages and combining the shared information and the language-specific information to counteract the instability of zero-shot translation. Experiments with Transformer on IWSLT17, Europarl, TED talks, and OPUS-100 datasets show that our method not only performs better than strong baselines in centered data conditions but also can easily fit non-centered data conditions. By further investigating the layer attribution, we show that our proposed method can disentangle the coupled representation in the correct direction.
