Ensemble Methods for Low-Resource Russian-Kyrgyz Machine Translation: When Diverse Models Beat Better Models
Year: 2026
Type: conference-paper
Abstract: We present our submission to the LoResMT 2026 Shared Task on Russian-Kyrgyz machine translation.Our approach demonstrates that ensembling diverse translation models with simple majority voting can significantly outperform individual models, achieving a +1.37 CHRF++ improvement over our best single model.Notably, we find that including "weaker" models in the ensemble improves overall performance, challenging the conventional assumption that ensembles should only combine top-performing systems.Our best submission achieved 49.31 CHRF++, placing 3rd in the Russian-Kyrgyz track, using only open-weight models without any fine-tuning on parallel Kyrgyz data.We also report several counter-intuitive findings: (1) simple voting outperforms quality-weighted selection, (2) more diverse models help even when individually weaker, and (3) post-processing "corrections" can hurt performance when reference translations contain similar artifacts.
Author: Adilet Metinov
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7140099592
FWCI:
Cites:
Cited by:
Related to: