JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages

JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages
MMLoSo 2025 IJCNLP-AACL Workshop Co-first author
Trung-Kiet Huynh*, Duy-Minh Dao-Sy*, Chi-Nguyen Tran*, Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dinh-Ha-Duong Nguyen, Dien Dinh, Hong-Buu-Long Nguyen
2nd Place, MMLoSo 2025 Language Challenge
Retrieval, LoRA-tuned NLLB and a lexical SMT branch, combined by Minimum Bayes Risk decoding for low-resource Indic translation.

JHARNA-MT: A Copy-Augmented Hybrid of LoRA-Tuned NLLB and Lexical SMT with Minimum Bayes Risk Decoding for Low-Resource Indic Languages

Huynh, T.-K., Dao-Sy, D.-M., Tran, C.-N., Nguyen-Lam, P.-Q., Pham, P.-H., Nguyen, D.-H.-D., Dinh, D., Nguyen, H.-B.-L. (2025). JHARNA-MT. MMLoSo 2025, pp. 114-120.