Deep code comment generation

Hu, Xing; Li, Ge; Xia, Xin; Lo, David; Jin, Zhi

doi:10.1145/3196321.3196334

Cited by 591 publications

(620 citation statements)

References 33 publications

Supporting

Mentioning

602

Contrasting

Unclassified

Order By: Relevance

“…We compared our approach to three neural network-based baseline methods, including vanilla seq2seq [18], Deep-Com [3], and HAD [4]. The last two methods are state-ofthe-art methods on comment generation.…”

Section: Methodsmentioning

confidence: 99%

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Wei

et al. 2019

2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

View full text Add to dashboard Cite

Code comment generation is a crucial task in the field of automatic software development. Most previous neural comment generation systems used an encoder-decoder neural network and encoded only information from source code as input. Software reuse is common in software development. However, this feature has not been introduced to existing systems. Inspired by the traditional IR-based approaches, we propose to use the existing comments of similar source code as exemplars to guide the comment generation process. Based on an open source search engine, we first retrieve a similar code and treat its comment as an exemplar. Then we applied a seq2seq neural network to conduct an exemplar-based comment generation. We evaluate our approach on a large-scale Java corpus, and experimental results demonstrate that our model significantly outperforms the state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Wei

et al. 2019

2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

View full text Add to dashboard Cite

show abstract

“…The code summarization task can be modeled as machine translation problem, so some models based on Seq2Seq paradigm [28] were proposed. Hu et al [16] proposed a structure-based traversal (SBT) algorithm in the encoder to flatten an AST and link the tokens in the source code with their AST node types.…”

Section: Code Summarizationmentioning

confidence: 99%

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

Xie

Zhang

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural language and programming language, recent studies have combined these two tasks to improve their performance. However, researchers have yet been able to effectively leverage the intrinsic connection between the two tasks as they train these tasks in a separate or pipeline manner, which means their performance can not be well balanced. In this paper, we propose a novel end-to-end model for the two tasks by introducing an additional code generation task. More specifically, we explicitly exploit the probabilistic correlation between code summarization and code generation with dual learning, and utilize the two encoders for code summarization and code generation to train the code retrieval task via multi-task learning. We have carried out extensive experiments on an existing dataset of SQL and Python, and results show that our model can significantly improve the results of the code retrieval task over the-state-of-art models, as well as achieve competitive performance in terms of BLEU score for the code summarization task.

show abstract

“…Referring to the process as "summarization" alludes to a history of work in Natural Language Processing of extractive summarization of documents -early attempts at code summarization involved choosing a set of n important words from code [18], [19] and then converting those words into complete sentences by placing them into sentence templates [2], [20]- [22]. A 2016 survey [23] highlights these approaches around the time that a vast majority of code summarization techniques began to be based on neural networks trained from big data input [10], [14], [24]- [27]. These NN-based approaches have proliferated, but suffer an Achilles' heel of reliance on very large, clean datasets of examples of code comments.…”

Section: A Source Code Summarizationmentioning

confidence: 99%

“…This application is especially useful for large repositories of legacy code such as the industrial situation described by McMillan et al [13]. A second application is in generating large datasets of code-comment pairs to serve as training data for automatic code summarization tools such as described by LeClair et al [10] and Hu et al [14]. These code summarization tools could reach a much wider audience (e.g.…”

Section: Introductionmentioning

confidence: 99%

Automatically Extracting Subroutine Summary Descriptions from Unstructured Comments

Eberhart

LeClair

McMillan

2020

2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)

View full text Add to dashboard Cite

descriptions of subroutines are short (usually one-sentence) natural language explanations of a subroutine's behavior and purpose in a program. These summaries are ubiquitous in documentation, and many tools such as JavaDocs and Doxygen generate documentation built around them. And yet, extracting summaries from unstructured source code repositories remains a difficult research problem -it is very difficult to generate clean structured documentation unless the summaries are annotated by programmers. This becomes a problem in large repositories of legacy code, since it is cost prohibitive to retroactively annotate summaries in dozens or hundreds of old programs. Likewise, it is a problem for creators of automatic documentation generation algorithms, since these algorithms usually must learn from large annotated datasets, which do not exist for many programming languages. In this paper, we present a semi-automated approach via crowdsourcing and a fully-automated approach for annotating summaries from unstructured code comments. We present experiments validating the approaches, and provide recommendations and cost estimates for automatically annotating large repositories.

show abstract

Deep code comment generation

Cited by 591 publications

References 33 publications

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Retrieve and Refine: Exemplar-Based Neural Comment Generation

Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning

Automatically Extracting Subroutine Summary Descriptions from Unstructured Comments

Contact Info

Product

Resources

About