Abstract
Neural machine translation has achieved great success in the past few years with the help of transformer architectures and large-scale bilingual corpora. However, when the source text gradually grows into an entire document, the performance of current methods for document-level machine translation (DocMT) is less satisfactory. Although the context is beneficial to the translation in general, it is difficult for traditional methods to utilize such long-range information. Previous studies on DocMT have concentrated on extra contents such as multiple surrounding sentences and input instances divided by a fixed length. We suppose that they ignore the structure inside the source text, which leads to under-utilization of the context. In this paper, we present a more sound paragraph-to-paragraph translation mode and explore whether discourse structure can improve DocMT. We introduce several methods from different perspectives, among which our RST-Att model with a multi-granularity attention mechanism based on the RST parsing tree works best. The experiments show that our method indeed utilizes discourse information and performs better than previous work.- Anthology ID:
- 2023.emnlp-main.857
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13889–13902
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.857
- DOI:
- 10.18653/v1/2023.emnlp-main.857
- Cite (ACL):
- Xinyu Hu and Xiaojun Wan. 2023. Exploring Discourse Structure in Document-level Machine Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13889–13902, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Exploring Discourse Structure in Document-level Machine Translation (Hu & Wan, EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.emnlp-main.857.pdf