Co-evolving data-driven and NLU-driven Synthesizers for Generating Code in Domain Growth and Data Scarcity

Jiasheng Gu, Zifan Nan, Zhiyuan Peng, Xipeng Shen, Dongkuan Xu


Abstract
Natural language programming automatically generates code based on a user’s text query. Recent solutions are either data-driven or natural language understanding (NLU)-driven. However, the data-driven synthesizer requires a large number of query-code pairs for training, which hinders its application to low-resource programming languages with growing domains whose functionality and grammar can be actively updated. NLU-driven synthesizers solve this problem, but their code generation is slow and their performance rapidly saturates in the presence of ever-increasing data. In this paper, we propose a circular training framework, Colead, which co-evolves both the data-driven synthesizer and the NLU-driven synthesizer to achieve high-quality code generation in the presence of data scarcity and domain growth. The NLU-driven synthesizer generates query-code pairs to update the data-driven synthesizer, which shares a part of its updated model to improve the NLU-driven synthesizers, enabling the co-evolution of both. Experiments show that Colead gives better results than the baselines in the presence of domain growth and data scarcity, and Colead consistently improves the performance of both data-driven and NLU-driven synthesizers over the co-evolvement.
Anthology ID:
2023.pandl-1.7
Volume:
Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
Month:
December
Year:
2023
Address:
Singapore
Editors:
Mihai Surdeanu, Ellen Riloff, Laura Chiticariu, Dayne Frietag, Gus Hahn-Powell, Clayton T. Morrison, Enrique Noriega-Atala, Rebecca Sharp, Marco Valenzuela-Escarcega
Venues:
PANDL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–74
Language:
URL:
https://aclanthology.org/2023.pandl-1.7
DOI:
10.18653/v1/2023.pandl-1.7
Bibkey:
Cite (ACL):
Jiasheng Gu, Zifan Nan, Zhiyuan Peng, Xipeng Shen, and Dongkuan Xu. 2023. Co-evolving data-driven and NLU-driven Synthesizers for Generating Code in Domain Growth and Data Scarcity. In Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning, pages 64–74, Singapore. Association for Computational Linguistics.
Cite (Informal):
Co-evolving data-driven and NLU-driven Synthesizers for Generating Code in Domain Growth and Data Scarcity (Gu et al., PANDL-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.pandl-1.7.pdf