[RETRACTED] Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training

Linqing Chen, Junhui Li, Zhengxian Gong, Boxing Chen, Weihua Luo, Min Zhang, Guodong Zhou


Abstract
Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. To this end, we propose two pre-training tasks. One learns to translate a sentence from source language to target language on the sentence-level parallel dataset while the other learns to translate a document from deliberately noised to original on the monolingual documents. Importantly, the two pre-training tasks are jointly and simultaneously learned via the same model, thereafter fine-tuned on scale-limited parallel documents from both sentence-level and document-level perspectives. Experimental results on four translation tasks show that our approach significantly improves translation performance. One nice property of our approach is that the fine-tuned model can be used to translate both sentences and documents.
Anthology ID:
2021.acl-long.222
Original:
2021.acl-long.222v1
Version 2:
2021.acl-long.222v2
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2851–2861
Language:
URL:
https://aclanthology.org/2021.acl-long.222
DOI:
10.18653/v1/2021.acl-long.222
PDF:
https://aclanthology.org/2021.acl-long.222.pdf
Video:
 https://aclanthology.org/2021.acl-long.222.mp4