MT2: Towards a Multi-Task Machine Translation Model with Translation-Specific In-Context Learning

Chunyou Li, Mingtong Liu, Hongxiao Zhang, Yufeng Chen, Jinan Xu, Ming Zhou


Abstract
Sentence-level translation, document-level translation, translation memory, and terminology constrained translation play an important role in machine translation. Most of the previous work uses separate models or methods to solve these tasks, which is not conducive to knowledge transfer of different tasks and increases the complexity of system construction. In this work, we explore the potential of pre-trained language model in machine translation tasks and propose a Multi-Task Machine Translation (MT2) model to integrate these translation tasks. We design a novel translation-specific In-Context Learning (ICL) paradigm for model training, in which all of the translation tasks can be modeled as context-learning tasks that integrate contextual information for performance improvement. Specifically, we propose a retrieval and alignment method to obtain a large scale context-enhancement training data, then we train the model in an in-context learning manner. Furthermore, we adopt two context-dependent training strategies to encourage the model to better understand and utilize contextual information for translation. Extensive experiments on translation memory, terminology constrained translation, document-level translation, and few-shot domain-adaptation tasks demonstrate the superior performance of our model, verifying the effectiveness of our proposed approach.
Anthology ID:
2023.emnlp-main.532
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:
8616–8627
Language:
URL:
https://aclanthology.org/2023.emnlp-main.532
DOI:
10.18653/v1/2023.emnlp-main.532
Bibkey:
Cite (ACL):
Chunyou Li, Mingtong Liu, Hongxiao Zhang, Yufeng Chen, Jinan Xu, and Ming Zhou. 2023. MT2: Towards a Multi-Task Machine Translation Model with Translation-Specific In-Context Learning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8616–8627, Singapore. Association for Computational Linguistics.
Cite (Informal):
MT2: Towards a Multi-Task Machine Translation Model with Translation-Specific In-Context Learning (Li et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.532.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.532.mp4