Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language
Mujadia Vandan, Mishra Pruthwik, Ahsan Arafat, M. Sharma Dipti
Abstract
With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA2-13B) achieves a comparable or higher overall correlation with human judgments for the considered Indian language pairs (Refer figure 1).- Anthology ID:
- 2023.icon-1.28
- Volume:
- Proceedings of the 20th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2023
- Address:
- Goa University, Goa, India
- Editors:
- D. Pawar Jyoti, Lalitha Devi Sobha
- Venue:
- ICON
- SIG:
- SIGLEX
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 357–369
- Language:
- URL:
- https://aclanthology.org/2023.icon-1.28
- DOI:
- Cite (ACL):
- Mujadia Vandan, Mishra Pruthwik, Ahsan Arafat, and M. Sharma Dipti. 2023. Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 357–369, Goa University, Goa, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language (Vandan et al., ICON 2023)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/2023.icon-1.28.pdf