Reasoning as Supportive Context for Machine Translation: A Case Study on Hindi to Bengali Language Pair

Kshetrimayum Boynao Singh, Saksham Singh, Partha Pakray, Asif Ekbal


Abstract
We investigate whether reasoning information can enhance machine translation when incorporated as supportive context during training and inference. Using Hindi-Bengali translation as a case study, we define five reasoning components: Key Terms, Syntactic, Semantic, Pragmatic, and Paraphrase. We conduct a complete ablation across all 31 possible combinations using Gemma-3-1B-Instruct and evaluate on multi-domain benchmark with BLEU, chrF, and TER. Evaluation results show that reasoning effectiveness depends on its type and composition rather than quantity. Combining multiple heterogeneous signals causes objective diffusion, degrading performance. The compact Semantic and Paraphrase combination proves optimal, and providing it during inference yields 23.86 BLEU compared to 22.12 from standard fine-tuning a +1.74 BLEU gain across eight domains. These findings demonstrate that targeted semantic guidance consistently and meaningfully improves the compact translation models.
Anthology ID:
2026.eamt-2.25
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
56–65
Language:
URL:
https://aclanthology.org/2026.eamt-2.25/
DOI:
Bibkey:
Cite (ACL):
Kshetrimayum Boynao Singh, Saksham Singh, Partha Pakray, and Asif Ekbal. 2026. Reasoning as Supportive Context for Machine Translation: A Case Study on Hindi to Bengali Language Pair. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 2), pages 56–65, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
Reasoning as Supportive Context for Machine Translation: A Case Study on Hindi to Bengali Language Pair (Singh et al., EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-2.25.pdf