A Simple and Effective Unified Encoder for Document-Level Machine Translation

• DOI: 10.18653/v1/2020.acl-main.321
• Publication Date: 2020-07-29T14:14:43Z
• Authors: Shuming Ma; Dongdong Zhang; Ming Zhou
• Keywords: Representation; Baseline (sea)

Most of the existing models for document-level machine translation adopt dual-encoder structures. The representation source sentences and contexts are modeled with two separate encoders. Although these can make use contexts, they do not fully model interaction between sentences, directly adapt to recent pre-training (e.g., BERT) which encodes multiple a single encoder. In this work, we propose simple effective unified encoder that outperform baseline in terms BLEU METEOR scores. Moreover, further boost performance our proposed model.