Causes and Cures for Interference in Multilingual Translation

Uri Shaham, Maha Elbayad, Vedanuj Goswami, Omer Levy, Shruti Bhosale


Abstract
Multilingual machine translation models can benefit from synergy between different language pairs, but also suffer from interference. While there is a growing number of sophisticated methods that aim to eliminate interference, our understanding of interference as a phenomenon is still limited. This work identifies the main factors that contribute to interference in multilingual machine translation. Through systematic experimentation, we find that interference (or synergy) are primarily determined by model size, data size, and the proportion of each language pair within the total dataset. We observe that substantial interference occurs mainly when the model is very small with respect to the available training data, and that using standard transformer configurations with less than one billion parameters largely alleviates interference and promotes synergy. Moreover, we show that tuning the sampling temperature to control the proportion of each language pair in the data is key to balancing the amount of interference between low and high resource language pairs effectively, and can lead to superior performance overall.
Anthology ID:
2023.acl-long.883
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15849–15863
Language:
URL:
https://aclanthology.org/2023.acl-long.883
DOI:
10.18653/v1/2023.acl-long.883
Award:
 Outstanding Paper Award
Bibkey:
Cite (ACL):
Uri Shaham, Maha Elbayad, Vedanuj Goswami, Omer Levy, and Shruti Bhosale. 2023. Causes and Cures for Interference in Multilingual Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15849–15863, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Causes and Cures for Interference in Multilingual Translation (Shaham et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.883.pdf
Video:
 https://aclanthology.org/2023.acl-long.883.mp4