Investigating the Effectiveness of Multiple Expert Models Collaboration

Ikumi Ito, Takumi Ito, Jun Suzuki, Kentaro Inui

Submission Type: Regular Short Paper

Submission Track: Machine Translation

Submission Track 2: Natural Language Generation

Keywords: machine translation, multi-domain translation, multiple model collaboration

TL;DR: This paper investigates the effectiveness of several machine translation models and aggregation methods in a multi-domain setting under a fair condition.

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.

Submission Number: 648