Compilable Neural Code Generation with Compiler Feedback

Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, Qun Liu

Abstract
Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code generation as text generation, either constrained by grammar structures in decoder, or driven by pre-trained language models on large-scale code corpus (e.g., CodeGPT, PLBART, and CodeT5). However, few of them account for compilability of the generated programs. To improve compilability of the generated programs, this paper proposes COMPCODER, a three-stage pipeline utilizing compiler feedback for compilable code generation, including language model fine-tuning, compilability reinforcement, and compilability discrimination. Comprehensive experiments on two code generation tasks demonstrate the effectiveness of our proposed approach, improving the success rate of compilation from 44.18 to 89.18 in code completion on average and from 70.3 to 96.2 in text-to-code generation, respectively, when comparing with the state-of-the-art CodeGPT.
Anthology ID:
2022.findings-acl.2
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9–19
Language:
URL:
https://aclanthology.org/2022.findings-acl.2
DOI:
10.18653/v1/2022.findings-acl.2
Bibkey:
Cite (ACL):
Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, and Qun Liu. 2022. Compilable Neural Code Generation with Compiler Feedback. In Findings of the Association for Computational Linguistics: ACL 2022, pages 9–19, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Compilable Neural Code Generation with Compiler Feedback (Wang et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.findings-acl.2.pdf
Data
CodeSearchNet
PDF Search