Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors.
Saved in:
| Title: | Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors. |
|---|---|
| Authors: | Peng, Yun1 ypeng@cse.cuhk.edu.hk, Gao, Shuzheng1 1155203205@link.cuhk.edu.hk, Gao, Cuiyun2 gaocuiyun@hit.edu.cn, Huo, Yintong1 ythuo@cse.cuhk.edu.hk, Lyu, Michael1 lyu@cse.cuhk.edu.hk |
| Source: | ICSE: International Conference on Software Engineering. 2024, p1-13. 13p. |
| Subjects: | Knowledge management, Design templates, Python programming language, Deep learning, Machine learning |
| Abstract: | As a dynamic programming language, Python has become increasingly popular in recent years. Although the dynamic type system of Python facilitates the developers in writing Python programs, it also brings type errors at run-time which are prevalent yet not easy to fix. There exist rule-based approaches for automatically repairing Python type errors. The approaches can generate accurate patches for the type errors covered by manually defined templates, but they require domain experts to design patch synthesis rules and suffer from low template coverage of real-world type errors. Learning-based approaches alleviate the manual efforts in designing patch synthesis rules and have become prevalent due to the recent advances in deep learning. Among the learning-based approaches, the prompt-based approach which leverages the knowledge base of code pre-trained models via pre-defined prompts, obtains state-of-the-art performance in general program repair tasks. However, such prompts are manually defined and do not involve any specific clues for repairing Python type errors, resulting in limited effectiveness. How to automatically improve prompts with the domain knowledge for type error repair is challenging yet under-explored. In this paper, we present TypeFix, a novel prompt-based approach with fix templates incorporated for repairing Python type errors. TypeFix first mines generalized fix templates via a novel hierarchical clustering algorithm. The identified fix templates indicate the common edit patterns and contexts of existing type error fixes. TypeFix then generates code prompts for code pre-trained models by employing the generalized fix templates as domain knowledge, in which the masks are adaptively located for each type error instead of being pre-determined. Experiments on two benchmarks, including BugsInPy and TypeBugs, show that TypeFix successfully repairs 26 and 55 type errors, outperforming the best baseline approach by 9 and 14, respectively. Besides, the proposed fix template mining approach can cover 75% of developers' patches in both benchmarks, increasing the best rule-based approach PyTER by more than 30%. [ABSTRACT FROM AUTHOR] |
| Copyright of ICSE: International Conference on Software Engineering is the property of Association for Computing Machinery and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 185196290 AccessLevel: 6 PubType: Conference PubTypeId: conference PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Peng%2C+Yun%22">Peng, Yun</searchLink><relatesTo>1</relatesTo><i> ypeng@cse.cuhk.edu.hk</i><br /><searchLink fieldCode="AR" term="%22Gao%2C+Shuzheng%22">Gao, Shuzheng</searchLink><relatesTo>1</relatesTo><i> 1155203205@link.cuhk.edu.hk</i><br /><searchLink fieldCode="AR" term="%22Gao%2C+Cuiyun%22">Gao, Cuiyun</searchLink><relatesTo>2</relatesTo><i> gaocuiyun@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Huo%2C+Yintong%22">Huo, Yintong</searchLink><relatesTo>1</relatesTo><i> ythuo@cse.cuhk.edu.hk</i><br /><searchLink fieldCode="AR" term="%22Lyu%2C+Michael%22">Lyu, Michael</searchLink><relatesTo>1</relatesTo><i> lyu@cse.cuhk.edu.hk</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22ICSE%3A+International+Conference+on+Software+Engineering%22">ICSE: International Conference on Software Engineering</searchLink>. 2024, p1-13. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Knowledge+management%22">Knowledge management</searchLink><br /><searchLink fieldCode="DE" term="%22Design+templates%22">Design templates</searchLink><br /><searchLink fieldCode="DE" term="%22Python+programming+language%22">Python programming language</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: As a dynamic programming language, Python has become increasingly popular in recent years. Although the dynamic type system of Python facilitates the developers in writing Python programs, it also brings type errors at run-time which are prevalent yet not easy to fix. There exist rule-based approaches for automatically repairing Python type errors. The approaches can generate accurate patches for the type errors covered by manually defined templates, but they require domain experts to design patch synthesis rules and suffer from low template coverage of real-world type errors. Learning-based approaches alleviate the manual efforts in designing patch synthesis rules and have become prevalent due to the recent advances in deep learning. Among the learning-based approaches, the prompt-based approach which leverages the knowledge base of code pre-trained models via pre-defined prompts, obtains state-of-the-art performance in general program repair tasks. However, such prompts are manually defined and do not involve any specific clues for repairing Python type errors, resulting in limited effectiveness. How to automatically improve prompts with the domain knowledge for type error repair is challenging yet under-explored. In this paper, we present TypeFix, a novel prompt-based approach with fix templates incorporated for repairing Python type errors. TypeFix first mines generalized fix templates via a novel hierarchical clustering algorithm. The identified fix templates indicate the common edit patterns and contexts of existing type error fixes. TypeFix then generates code prompts for code pre-trained models by employing the generalized fix templates as domain knowledge, in which the masks are adaptively located for each type error instead of being pre-determined. Experiments on two benchmarks, including BugsInPy and TypeBugs, show that TypeFix successfully repairs 26 and 55 type errors, outperforming the best baseline approach by 9 and 14, respectively. Besides, the proposed fix template mining approach can cover 75% of developers' patches in both benchmarks, increasing the best rule-based approach PyTER by more than 30%. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of ICSE: International Conference on Software Engineering is the property of Association for Computing Machinery and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=185196290 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1145/3597503.3608132 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 1 Subjects: – SubjectFull: Knowledge management Type: general – SubjectFull: Design templates Type: general – SubjectFull: Python programming language Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Machine learning Type: general Titles: – TitleFull: Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Peng, Yun – PersonEntity: Name: NameFull: Gao, Shuzheng – PersonEntity: Name: NameFull: Gao, Cuiyun – PersonEntity: Name: NameFull: Huo, Yintong – PersonEntity: Name: NameFull: Lyu, Michael IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: 2024 Type: published Y: 2024 Titles: – TitleFull: ICSE: International Conference on Software Engineering Type: main |
| ResultId | 1 |
