Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation-猫眼课题宝

DOI：

发表时间：

2019-06

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Chenhui Chu;Raj Dabre

在本文中，我们提出了两种新的方法，用于只关注神经机器翻译（NMT）模型的域自适应，即，Transformer。我们的方法专注于通过学习领域专门的隐藏状态表示或每个领域的预测偏差来训练多个领域的单个翻译模型。我们将我们的方法与先前提出的称为混合微调的黑盒方法相结合，该方法对于域自适应非常有效。此外，我们将多语言的领域适应框架。实验表明，多语言多领域自适应可以显著改善资源贫乏的域内和资源丰富的域外翻译，并且我们的方法与混合微调的组合实现了最佳性能。

In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transformer. Our methods focus on training a single translation model for multiple domains by either learning domain specialized hidden state representations or predictor biases for each domain. We combine our methods with a previously proposed black-box method called mixed fine tuning, which is known to be highly effective for domain adaptation. In addition, we incorporate multilingualism into the domain adaptation framework. Experiments show that multilingual multi-domain adaptation can significantly improve both resource-poor in-domain and resource-rich out-of-domain translations, and the combination of our methods with mixed fine tuning achieves the best performance.

Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation

文献摘要

相似文献