Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features

Mengyu Bu, Shuhao Gu, Yang Feng

Abstract
The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models need to share knowledge across languages, which can be achieved through auxiliary tasks for learning a universal representation or cross-lingual mapping. To this end, we propose to exploit both semantic and linguistic features between multiple languages to enhance multilingual translation. On the encoder side, we introduce a disentangling learning task that aligns encoder representations by disentangling semantic and linguistic features, thus facilitating knowledge transfer while preserving complete information. On the decoder side, we leverage a linguistic encoder to integrate low-level linguistic features to assist in the target language generation. Experimental results on multilingual datasets demonstrate significant improvement in zero-shot translation compared to the baseline system, while maintaining performance in supervised translation. Further analysis validates the effectiveness of our method in leveraging both semantic and linguistic features.
Anthology ID:
2024.findings-acl.620
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10410–10423
Language:
URL:
https://aclanthology.org/2024.findings-acl.620
DOI:
10.18653/v1/2024.findings-acl.620
Bibkey:
Cite (ACL):
Mengyu Bu, Shuhao Gu, and Yang Feng. 2024. Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10410–10423, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features (Bu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-acl.620.pdf
PDF Search