Leveraging meta-data of code for adapting prompt tuning for code summarization

Zhihua Jiang; Lei Wang; Dongning Rao

doi:10.1007/s10489-024-06197-0

ScienceGate Book Chapters

JOURNAL ARTICLE

Leveraging meta-data of code for adapting prompt tuning for code summarization

Zhihua Jiang Lei Wang Dongning Rao

Year: 2024 Journal: Applied Intelligence Vol: 55 (3) Publisher: Springer Science+Business Media

DOI: 10.1007/s10489-024-06197-0

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Automatic summarization Task (project management) Code (set theory) Benchmark (surveying) Abstract syntax tree Metric (unit) Artificial intelligence Source code Syntax Natural language processing Programming language

Metrics

Cited By

1.53

FWCI (Field Weighted Citation Impact)

Refs

0.84

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Software Engineering Research

Physical Sciences → Computer Science → Information Systems

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Natural Language Processing Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Leveraging meta-data of code for adapting prompt tuning for code summarization

Metrics

Citation History

Topics

Related Documents

Improve Code Summarization via Prompt-Tuning CodeT5

Context-Focused Prompt Tuning Pre-Trained Code Models to Improve Code Summarization

Prompt Learning for Source Code Summarization

Leveraging Comment Retrieval for Code Summarization

A Two-Stage Framework Integrating Prompt Learning and Fine-Tuning for Code Summarization