RAR: Retrieval-augmented retrieval for code generation in low resource languages
Avik Dutta, Mukul Singh, Gust Verbruggen, Sumit Gulwani, Vu Le
Abstract
Language models struggle in generating code for low-resource programming languages, since these are underrepresented in training data. Either examples or documentation are commonly used for improved code generation. We propose to use both types of information together and present retrieval augmented retrieval (RAR) as a two-step method for selecting relevant examples and documentation. Experiments on three low-resource languages (Power Query M, OfficeScript and Excel formulas) show that RAR outperforms independently example and grammar retrieval (+2.81–26.14%). Interestingly, we show that two-step retrieval selects better examples and documentation when used independently as well.
BibTeX
@inproceedings{dutta-etal-2024-rar,
title = "{RAR}: Retrieval-augmented retrieval for code generation in low resource languages",
author = "Dutta, Avik and
Singh, Mukul and
Verbruggen, Gust and
Gulwani, Sumit and
Le, Vu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1199/",
doi = "10.18653/v1/2024.emnlp-main.1199",
pages = "21506--21515"
}