Abstract
“Document-level neural machine translation (NMT) has garnered considerable attention sincethe emergence of various context-aware NMT models. However, these static NMT models aretrained on fixed parallel datasets, thus lacking awareness of the target document during infer-ence. In order to alleviate this limitation, we propose a dynamic adapter-translator frameworkfor context-aware NMT, which adapts the trained NMT model to the input document prior totranslation. Specifically, the document adapter reconstructs the scrambled portion of the originaldocument from a deliberately corrupted version, thereby reducing the performance disparity be-tween training and inference. To achieve this, we employ an adaptation process in both the train-ing and inference stages. Our experimental results on document-level translation benchmarksdemonstrate significant enhancements in translation performance, underscoring the necessity ofdynamic adaptation for context-aware translation and the efficacy of our methodologies.Introduction”- Anthology ID:
- 2023.ccl-1.57
- Volume:
- Proceedings of the 22nd Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2023
- Address:
- Harbin, China
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 665–676
- Language:
- English
- URL:
- https://aclanthology.org/2023.ccl-1.57
- DOI:
- Cite (ACL):
- Chen Linqing and Wang Weilei. 2023. Dynamic-FACT: A Dynamic Framework for Adaptive Context-Aware Translation. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 665–676, Harbin, China. Chinese Information Processing Society of China.
- Cite (Informal):
- Dynamic-FACT: A Dynamic Framework for Adaptive Context-Aware Translation (Linqing & Weilei, CCL 2023)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2023.ccl-1.57.pdf