# Modeling Discourse Structure for Document-level Neural Machine Translation

arXiv: https://arxiv.org/abs/2006.04721 · HTML: https://mlsanity.com/paper/2006.04721/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 11 of 11)

- [Large language models effectively leverage document-level context for literary translation, but critical errors persist](https://mlsanity.com/paper/2304.03245/) (2023)
- [Measuring and Increasing Context Usage in Context-Aware Machine Translation](https://mlsanity.com/paper/2105.03482/) (2021)
- [Do Context-Aware Translation Models Pay the Right Attention?](https://mlsanity.com/paper/2105.06977/) (2021)
- [Towards Making the Most of Dialogue Characteristics for Neural Chat Translation](https://mlsanity.com/paper/2109.00668/) (2021)
- [DOCmT5: Document-Level Pretraining of Multilingual Language Models](https://mlsanity.com/paper/2112.08709/) (2021)
- [Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents](https://mlsanity.com/paper/2109.10341/) (2021)
- [Text revision in Scientific Writing Assistance: An Overview](https://mlsanity.com/paper/2303.16726/) (2023)
- [Can we obtain significant success in RST discourse parsing by using Large Language Models?](https://mlsanity.com/paper/2403.05065/) (2024)
- [Distributed Marker Representation for Ambiguous Discourse Markers and Entangled Relations](https://mlsanity.com/paper/2306.10658/) (2023)
- [Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models](https://mlsanity.com/paper/2212.07752/) (2022)
- [Context-Aware Dialectal Arabic Machine Translation with Interactive Region and Register Selection](https://mlsanity.com/paper/2604.06456/) (2026)

## Abstract (arXiv)

Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be translated, which has shown effective in other tasks. In this paper, we propose to improve document-level NMT with the aid of discourse structure information. Our encoder is based on a hierarchical attention network (HAN). Specifically, we first parse the input document to obtain its discourse structure. Then, we introduce a Transformer-based path encoder to embed the discourse structure information of each word. Finally, we combine the discourse structure information with the word embedding before it is fed into the encoder. Experimental results on the English-to-German dataset show that our model can significantly outperform both Transformer and Transformer+HAN.