Explain-then-translate: an analysis on improving program translation with self-generated explanations
Zilu Tang, Mayank Agarwal, Alexander Shypula, Bailin Wang, Derry Wijaya, Jie Chen, Yoon Kim
Abstract
This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models. Across three types of explanations and 19 programming languages constructed from the MultiPL-E dataset, we find the explanations to be particularly effective in the zero-shot case, improving performance by 12% on average. Improvements with natural language explanations are particularly pronounced on difficult programs. We release our dataset, code, and canonical solutions in all 19 languages.- Anthology ID:
- 2023.findings-emnlp.119
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1741–1788
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.119
- DOI:
- 10.18653/v1/2023.findings-emnlp.119
- Cite (ACL):
- Zilu Tang, Mayank Agarwal, Alexander Shypula, Bailin Wang, Derry Wijaya, Jie Chen, and Yoon Kim. 2023. Explain-then-translate: an analysis on improving program translation with self-generated explanations. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1741–1788, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Explain-then-translate: an analysis on improving program translation with self-generated explanations (Tang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-emnlp.119.pdf