Hierarchical modeling of global context for document-level neural machine translation

Xin Tan, Longyin Zhang, Deyi Xiong, Guodong ZhouOpenReview 2025 · OpenReview

Abstract

Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context for translation. In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT). This is done through a sentence encoder to capture intra-sentence dependencies and a document encoder to model document-level inter-sentence consistency and coherence. With this hierarchical architecture, we feedback the extracted global document context to each word in a top-down fashion to distinguish different translations of a word according to its specific surrounding context. In addition, since large-scale in-domain document-level parallel corpora are usually unavailable, we use a two-step training strategy to take advantage of a large-scale corpus with out-of-domain parallel sentence pairs and a small-scale corpus with in-domain parallel document pairs to achieve the domain adaptability. Experimental results on several benchmark corpora show that our proposed model can significantly improve document-level translation performance over several strong NMT baselines.
BibTeX
@misc{tan2025hierarchical,
  author = {Xin Tan and Longyin Zhang and Deyi Xiong and Guodong Zhou},
  title = {{Hierarchical modeling of global context for document-level neural machine translation}},
  year = {2025},
  url = {https://openreview.net/forum?id=id2eHVmcDA},
  howpublished = {OpenReview},
}

Loading related content...

Figure