Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents

Biao Zhang, Ankur Bapna, Melvin Johnson, Ali Dabirmoghaddam, Naveen Arivazhagan, Orhan Firat


Abstract
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there’s a shortage of parallel documents, although parallel sentences are readily available. In this paper, we study whether and how contextual modeling in DocNMT is transferable via multilingual modeling. We focus on the scenario of zero-shot transfer from teacher languages with document level data to student languages with no documents but sentence level data, and for the first time treat document-level translation as a transfer learning problem. Using simple concatenation-based DocNMT, we explore the effect of 3 factors on the transfer: the number of teacher languages with document level data, the balance between document and sentence level data at training, and the data condition of parallel documents (genuine vs. back-translated). Our experiments on Europarl-7 and IWSLT-10 show the feasibility of multilingual transfer for DocNMT, particularly on document-specific metrics. We observe that more teacher languages and adequate data balance both contribute to better transfer quality. Surprisingly, the transfer is less sensitive to the data condition, where multilingual DocNMT delivers decent performance with either back-translated or genuine document pairs.
Anthology ID:
2022.acl-long.287
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4176–4192
Language:
URL:
https://aclanthology.org/2022.acl-long.287
DOI:
10.18653/v1/2022.acl-long.287
Bibkey:
Cite (ACL):
Biao Zhang, Ankur Bapna, Melvin Johnson, Ali Dabirmoghaddam, Naveen Arivazhagan, and Orhan Firat. 2022. Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4176–4192, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents (Zhang et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.287.pdf
Video:
 https://aclanthology.org/2022.acl-long.287.mp4