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.
Original language | English |
---|---|
Title of host publication | Long Papers |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 15849-15863 |
Number of pages | 15 |
ISBN (Electronic) | 9781959429722 |
DOIs | |
State | Published - 2023 |
Event | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada Duration: 9 Jul 2023 → 14 Jul 2023 |
Publication series
Name | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
---|---|
Volume | 1 |
ISSN (Print) | 0736-587X |
Conference
Conference | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 |
---|---|
Country/Territory | Canada |
City | Toronto |
Period | 9/07/23 → 14/07/23 |
Bibliographical note
Publisher Copyright:© 2023 Association for Computational Linguistics.
Funding
This research is supported by the Yandex Initiative in Machine Learning. We thank Maor Ivgi, Yilin Yang, Jean Maillard, and Ves Stoyanov for their valuable feedback.
Funders | Funder number |
---|---|
Yandex Initiative in Machine Learning |