EMNLP 2023short findings0 citations
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.
machine translationmulti-domain translationmultiple model collaboration
BibTeX
@inproceedings{
ito2023investigating,
title={Investigating the Effectiveness of Multiple Expert Models Collaboration},
author={Ikumi Ito and Takumi Ito and Jun Suzuki and Kentaro Inui},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=6Jqa4YmUMf}
}