Investigating the Effectiveness of Multiple Expert Models Collaboration

Ikumi Ito, Takumi Ito, Jun Suzuki, Kentaro Inui


Abstract
This paper aims to investigate the effectiveness of several machine translation (MT) models and aggregation methods in a multi-domain setting under fair conditions and explore a direction for tackling multi-domain MT. We mainly compare the performance of the single model approach by jointly training all domains and the multi-expert models approach with a particular aggregation strategy. We conduct experiments on multiple domain datasets and demonstrate that a combination of smaller domain expert models can outperform a larger model trained for all domain data.
Anthology ID:
2023.findings-emnlp.960
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14393–14404
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.960
DOI:
10.18653/v1/2023.findings-emnlp.960
Bibkey:
Cite (ACL):
Ikumi Ito, Takumi Ito, Jun Suzuki, and Kentaro Inui. 2023. Investigating the Effectiveness of Multiple Expert Models Collaboration. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14393–14404, Singapore. Association for Computational Linguistics.
Cite (Informal):
Investigating the Effectiveness of Multiple Expert Models Collaboration (Ito et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.960.pdf