论文标题
三角转移：冻结三角形机器翻译的枢轴
Triangular Transfer: Freezing the Pivot for Triangular Machine Translation
论文作者
论文摘要
三角形机器翻译是低资源机器翻译的特殊情况，其中兴趣的语言对具有有限的并行数据，但是两种语言都具有具有枢轴语言的丰富并行数据。自然，三角机器翻译的关键是成功利用了这种辅助数据。在这项工作中，我们提出了一种基于转移学习的方法，该方法利用了所有类型的辅助数据。当我们训练辅助源 - 彼此和枢轴 - 目标翻译模型时，我们使用预先训练的语言模型初始化了枢轴侧的某些参数，并冻结它们以鼓励两个翻译模型在相同的枢轴语言空间中工作，以便它们可以顺利传输到源目标转换模型。实验表明，我们的方法可以胜过以前的方法。
Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant parallel data with a pivot language. Naturally, the key to triangular machine translation is the successful exploitation of such auxiliary data. In this work, we propose a transfer-learning-based approach that utilizes all types of auxiliary data. As we train auxiliary source-pivot and pivot-target translation models, we initialize some parameters of the pivot side with a pre-trained language model and freeze them to encourage both translation models to work in the same pivot language space, so that they can be smoothly transferred to the source-target translation model. Experiments show that our approach can outperform previous ones.
