✳flâneur — a map of the web's best reading

[2207.05987] DocPrompting: Generating Code by Retrieving the Docs

arxiv.org · 754 words · saved by 1 readers

Publicly available source-code libraries are continuously growing and changing. This makes it impossible for models of code to keep current with all available APIs by simply training these models on existing code repositories. Thus, existing models inherently cannot generalize to using unseen functions and libraries, because these would never appear in the training data. In contrast, when human programmers use functions and libraries for the first time, they frequently refer to textual resources such as code manuals and documentation, to explore and understand the available functionality. Inspired by this observation, we introduce DocPrompting: a natural-language-to-code generation approach that explicitly leverages documentation by (1) retrieving the relevant documentation pieces given an NL intent, and (2) generating code based on the NL intent and the retrieved documentation. DocPrompting is general: it can be applied to any programming language and is agnostic to the underlying neural model. We demonstrate that DocPrompting consistently improves NL-to-code models: DocPrompting improves strong base models such as CodeT5 by 2.85% in pass@1 (52% relative gain) and 4.39% in pass@10 (30% relative gain) in execution-based evaluation on the popular Python CoNaLa benchmark; on a new Bash dataset tldr, DocPrompting improves CodeT5 and GPT-Neo1.3B by up to absolute 6.9% exact match.

[2207.05987] DocPrompting: Generating Code by Retrieving the Docs Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2207.05987 (cs) [Submitted on 13 Jul 2022 ( v1 ), last revised 18 Feb 2023 (this version, v3)] Title: DocPrompting: Generating Code by Retrieving the Docs Authors: Shuyan Zhou , Uri Alon , Frank F. Xu , Zhiruo Wang , Zhengbao Jiang , Graham Neubig View a PDF of the paper titled DocPrompting: Generating Code by Retrieving the Docs, by Shuya

Explore this link on the map →

related reading