Rethinking Document-level Neural Machine Translation

Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, Lei Li


Abstract
This paper does not aim at introducing a novel model for document-level neural machine translation. Instead, we head back to the original Transformer model and hope to answer the following question: Is the capacity of current models strong enough for document-level translation? Interestingly, we observe that the original Transformer with appropriate training techniques can achieve strong results for document translation, even with a length of 2000 words. We evaluate this model and several recent approaches on nine document-level datasets and two sentence-level datasets across six languages. Experiments show that document-level Transformer models outperforms sentence-level ones and many previous methods in a comprehensive set of metrics, including BLEU, four lexical indices, three newly proposed assistant linguistic indicators, and human evaluation.
Anthology ID:
2022.findings-acl.279
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3537–3548
Language:
URL:
https://aclanthology.org/2022.findings-acl.279
DOI:
10.18653/v1/2022.findings-acl.279
Bibkey:
Cite (ACL):
Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, and Lei Li. 2022. Rethinking Document-level Neural Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3537–3548, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Rethinking Document-level Neural Machine Translation (Sun et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.findings-acl.279.pdf
Code
 sunzewei2715/Doc2Doc_NMT