Source Code Summarization

37 papers with code • 9 benchmarks • 7 datasets

Code Summarization is a task that tries to comprehend code and automatically generate descriptions directly from the source code.

Source: Improving Automatic Source Code Summarization via Deep Reinforcement Learning

Libraries

Use these libraries to find Source Code Summarization models and implementations
2 papers
21

Latest papers with no code

EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

no code yet • 26 Aug 2023

Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code.

Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization

no code yet • 16 May 2023

The attention mechanism learns to connect features in source code to specific words to use when generating natural language descriptions.

Meta Learning for Code Summarization

no code yet • 20 Jan 2022

Source code summarization is the task of generating a high-level natural language description for a segment of programming language code.

Retrieval-based Layer-wise Adaptive Transformer for Source Code Summarization

no code yet • ACL ARR November 2021

We adopt the Abstract Syntax Tree (AST) and graph convolution to model the structural information and the Transformer to model the sequential information.

Meta Learning for Code Summarization

no code yet • ACL ARR November 2021

Source code summarization is the task of generating a high-level natural language description for a segment of programming language code.

Code Structure Guided Transformer for Source Code Summarization

no code yet • 19 Apr 2021

Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance.

Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach

no code yet • 21 Mar 2021

Code summaries are brief natural language descriptions of source code pieces.

WheaCha: A Method for Explaining the Predictions of Models of Code

no code yet • 9 Feb 2021

Attribution methods have emerged as a popular approach to interpreting model predictions based on the relevance of input features.

GN-Transformer: Fusing AST and Source Code information in Graph Networks

no code yet • 1 Jan 2021

As opposed to natural languages, source code understanding is influenced by grammar relations between tokens regardless of their identifier name.

Automatic Source Code Summarization via Reinforcement Learning

no code yet • CUHK Course IERG5350 2020

For large-scale systems (e. g., cloud computing systems) with billions lines of codes, the majority of its maintenance effort is code management.