AutoComment: Mining question and answer sites for automatic comment generation

Wong, Edmund; Yang, Jinqiu; Tan, Lin

doi:10.1109/ase.2013.6693113

Cited by 214 publications

(163 citation statements)

References 13 publications

Supporting

Mentioning

163

Contrasting

Order By: Relevance

“…Our result shows that 23.7% of the generated code comments are good. The yield and accuracy are both low despite having a larger set of source code for mining compared to our previous work [7]. However, we analyzed the key observations in the results and reported the good code comments to developers.…”

Section: Introductionmentioning

confidence: 89%

“…The reason is if a code segment had never been discussed on a Q&A website, then AutoComment cannot generate a comment for the detected code segments that are similar, which limits the yield. Based on our user study [7], we learnt that comments that are written for easy-to-understand code (no comment is needed to help comprehension) are less useful.…”

Section: Introductionmentioning

confidence: 99%

“…Mining human written comments from software repositories have four main challenges over our previous work [7], which mines human written comments from Q&A sites:…”

Section: Introductionmentioning

confidence: 99%

“…This is a problem because a single code segment can have many comment candidates. In our previous work [7], Q&A sites often disallow duplicate questions, we typically have less than four comment candidates when mining Q&A sites. Therefore, we need new approaches to rank the multiple matched comment candidates.…”

Section: Introductionmentioning

confidence: 99%

“…Our previous work AutoComment [7] mined a large-scale question and answer (Q&A) website, Stack Overflow [8], to extract and improve human written descriptions for automatic comment generation. AutoComment extracted code segments from Stack Overflow, and identified their corresponding descriptions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

CloCom: Mining existing source code for automatic comment generation

Wong

Liu

Tan

2015

2015 IEEE 22nd International Conference on Software Analysis, Evolution, and Reengineering (SANER)

Self Cite

134

View full text Add to dashboard Cite

Abstract-Code comments are an integral part of software development. They improve program comprehension and software maintainability. The lack of code comments is a common problem in the software industry. Therefore, it is beneficial to generate code comments automatically. In this paper, we propose a general approach to generate code comments automatically by analyzing existing software repositories. We apply code clone detection techniques to discover similar code segments and use the comments from some code segments to describe the other similar code segments. We leverage natural language processing techniques to select relevant comment sentences.In our evaluation, we analyze 42 million lines of code from 1,005 open source projects from GitHub, and use them to generate 359 code comments for 21 Java projects. We manually evaluate the generated code comments and find that only 23.7% of the generated code comments are good. We report to the developers the good code comments, whose code segments do not have an existing code comment. Amongst the reported code comments, seven have been confirmed by the developers as good and committable to the software repository while the rest await for developers' confirmation. Although our approach can generate good and committable comments, we still have to improve the yield and accuracy of the proposed approach before it can be used in practice with full automation.

show abstract

Section: Introductionmentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

“…Mining human written comments from software repositories have four main challenges over our previous work [7], which mines human written comments from Q&A sites:…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CloCom: Mining existing source code for automatic comment generation

Wong

Liu

Tan

2015

2015 IEEE 22nd International Conference on Software Analysis, Evolution, and Reengineering (SANER)

Self Cite

134

View full text Add to dashboard Cite

show abstract

Automated feature discovery via sentence selection and source code summarization

McBurney

Liu

McMillan

2016

J. Softw. Evol. and Proc.

View full text Add to dashboard Cite

Programs are, in essence, a collection of implemented features. Feature discovery in software engineering is the task of identifying key functionalities that a program implements. Manual feature discovery can be time consuming and expensive, leading to automatic feature discovery tools being developed. However, these approaches typically only describe features using lists of keywords, which can be difficult for readers who are not already familiar with the source code. An alternative to keyword lists is sentence selection, in which one sentence is chosen from among the sentences in a text document to describe that document. Sentence selection has been widely studied in the context of natural language summarization but is only beginning to be explored as a solution to feature discovery. In this paper, we compare four sentence selection strategies for the purpose of feature discovery. Two are off-the-shelf approaches, while two are adaptations we propose. We present our findings as guidelines and recommendations to designers of feature discovery tools.

show abstract

PassSum: Leveraging paths of abstract syntax trees and self‐supervision for code summarization

Niu,

Li,

et al. 2023

J Software Evolu Process

View full text Add to dashboard Cite

Code summarization is to provide a high‐level comment for a code snippet that typically describes the function and intent of the given code. Recent years have seen the successful application of data‐driven code summarization. To improve the performance of the model, numerous approaches use abstract syntax trees (ASTs) to represent the structural information of the code, which is considered by most researchers to be the main factor that distinguishes code from natural language. Then, such data‐driven methods are trained on large‐scale labeled datasets to obtain a model with strong generalization capabilities that can be applied to new examples. Nevertheless, we argue that state‐of‐the‐art approaches suffer from two key weaknesses: (1) inefficient encoding of ASTs; (2) reliance on a large labeled corpus for model training. As a result, such drawbacks lead to (1) oversized model, slow training, information loss and instability; (2) inability to be applied to programming languages with only a small amount of labeled data. In light of these weaknesses, we propose PassSum, a code summarization approach that addresses the aforementioned weaknesses via (1) a novel input representation which contains an efficient AST encoding method; (2) introducing three pretraining objectives and pretraining our model with a large amount of (easy‐to‐obtain) unlabeled data under the guidance of self‐supervised learning. Experimental results on code summarization for Java, Python, and Ruby methods demonstrate the superiority of PassSum to state‐of‐the‐art methods. Further experiments demonstrate that the input representation we use has both temporal and spatial advantages in addition to performance leadership. In addition, pretraining is also shown to make the model more generalizable with less labeled data, and also to speed up the convergence of the model during training.

show abstract

AutoComment: Mining question and answer sites for automatic comment generation

Cited by 214 publications

References 13 publications

CloCom: Mining existing source code for automatic comment generation

CloCom: Mining existing source code for automatic comment generation

Automated feature discovery via sentence selection and source code summarization

PassSum: Leveraging paths of abstract syntax trees and self‐supervision for code summarization

Contact Info

Product

Resources

About