English

Improving Neural Machine Translation with Pre-trained Representation

Computation and Language 2019-08-22 v1

Abstract

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or extracting information from word embedding. In contrast, the power of sentence-level contextual knowledge which is more complex and diverse, playing an important role in natural language generation, has not been fully exploited. In this paper, we propose a novel structure which could leverage monolingual data to acquire sentence-level contextual representations. Then, we design a framework for integrating both source and target sentence-level representations into NMT model to improve the translation quality. Experimental results on Chinese-English, German-English machine translation tasks show that our proposed model achieves improvement over strong Transformer baselines, while experiments on English-Turkish further demonstrate the effectiveness of our approach in the low-resource scenario.

Keywords

Cite

@article{arxiv.1908.07688,
  title  = {Improving Neural Machine Translation with Pre-trained Representation},
  author = {Rongxiang Weng and Heng Yu and Shujian Huang and Weihua Luo and Jiajun Chen},
  journal= {arXiv preprint arXiv:1908.07688},
  year   = {2019}
}

Comments

In Progress

R2 v1 2026-06-23T10:52:51.542Z