Towards automatically generating summary comments for Java methods

By G. Sridhara, Emily Hill, Divya Muppaneni, Lori L. Pollock, K. Vijay-Shanker. International Conference on Automated Software Engineering, 2010

572 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/d86c23307f9c590dad1a37688080b9140b11d0cc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Software

Citations in the corpus

A Neural Model for Generating Natural Language Summaries of Program Subroutines (2019, methodology): “Our scoping of our target problem is consistent with the problem definition in many papers on code summarization [1], [12], [13], [22], [25].”
A Transformer-based Approach for Source Code Summarization (2020, background): “A natural language summary of source code facilitates program comprehension by reducing developers’ efforts signiﬁcantly (Sridhara et al., 2010).”
Summarizing Source Code using a Neural Attention Model (2016, methodology): “Sridhara et al. (2010) present a pipeline that generates summaries of Java methods by selecting relevant content and generating phrases using templates to describe them.”
On the naturalness of software (2016, methodology): “Summarization and Concern Location A line of work on code summarization 9, 47, 48 uses semantic properties inferred by static analysis, rather than the “natural” regularities of software corpora capturable in statistical models; it is complementary to ours: properties derived by static analysis (as…”
Improving Automatic Source Code Summarization via Deep Reinforcement Learning (2018, methodology): “As far as we know, most of existing code summarization methods learn the semantic representation of source codes based on statistical language models [9], [4], and then generate comments based on templates or rules [10].”
Few-shot training LLMs for project-specific code-summarization (2022, background): “Good quality comments can benefit the developers by contributing to both the development and maintenance process [20].”
CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning (2019, methodology): “ures the cosine similarity between them. Code Annotation. Code annotation/summarization has drawn a lot of attention in recent years. Earlier works tackled the problem using template-based approaches [37, 49] and topic n-grams models [38] while the recent techniques [2, 19–22, 31] are mostly built u”
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2023, unknown): “GPT-3.”
Retrieval-based Neural Source Code Summarization (2020, methodology): “In addition, Srid-hara et al. [52] design heuristics to choose statements from Java methods, and use the Software Word Usage Model (SWUM) to identify keywords from those statements and create summaries though manually-crafted templates.”
Natural Language Models for Predicting Programming Comments (2013, background): “Code commenting not only provides a summarization of the conceptual idea behind the code (Sridhara et al., 2010), but can also be viewed as a form of document expansion where the comment contains significant terms relevant to the described code.”
Automatically generating commit messages from diffs using neural machine translation (2017, unknown): “For example, Sridhara et al. has designed a Natural Language Generation (NLG) system to create summaries of Java methods [50].”
Measuring Program Comprehension: A Large-Scale Field Study with Professionals (2018, background): “the automated generation of comments [38], [54], [55], [61], and documents [25], [35].”
Improved Code Summarization via a Graph Neural Network (2020, methodology): “At first, the dominant strategy was based on sentence templates and heuristics derived from empirical studies [15, 36, 40, 44, 50, 51].”
RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation (2024, unknown): “Early methods were rule-based or template-driven (Haiduc et al., 2010; Sridhara et al., 2010; Moreno et al., 2013; Rodeghero et al., 2014).”
Deep Code Comment Generation (2018, methodology): “Previous studies have shown that good comments are important to program comprehension, since developers can understand the meaning of a piece of code by using the natural language description of the comments [35].”
On the localness of software (2014, methodology): “on GitHub and BitBucket), software engineering researchers have turned to empirical methods to study the process of developing and maintaining software [11, 27, 38, 40, 42–45, 47, 49].”
On the naturalness of software (2012, background): “This line of work aims to generate natural language descriptions (summaries) of code [15–17].”