Extracting Code Segments and Their Descriptions from Research Articles

Chatterjee, Preetha; Gause, Benjamin; Hedinger, Hunter; Pollock, Lori

doi:10.1109/msr.2017.10

Cited by 9 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several early studies [Wong, Yang e Tan 2013, Rahman, Roy e Keivanloo 2015, Xu et al 2017, Chatterjee et al 2017, Hu et al 2018, Wong, Liu e Tan 2015 propose automatic approaches to extract explanations to code. For this, they explore lexical properties usually in combination with strategies like clone detection [Wong, Yang e Tan 2013, Wong, Liu e Tan 2015], topics (like LDA) [Rahman, Roy e Keivanloo 2015], word embeddings [Xu et al 2017], machine learning [Chatterjee et al 2017] and deep learning [Hu et al 2018]. Wong et al [Wong, Yang e Tan 2013] propose a series of heuristics to match the code with natural language.…”

Section: Code Explanation Generationmentioning

confidence: 99%

See 1 more Smart Citation

CROKAGE: Effective Solution Recommendation for Programming Tasks by Leveraging Crowd Knowledge

Silva

Maia

2021

Anais Estendidos Do XII Congresso Brasileiro De Software: Teoria E Prática (CBSoft Estendido 2021)

View full text Add to dashboard Cite

Developers often search for relevant code examples on the web for their programming tasks. Unfortunately, they face three major problems. First, they frequently need to read and analyse multiple results from the search engines to obtain a satisfactory solution. Second, the search is impaired due to a lexical gap between the query (task description) and the information in the solution (e.g., code example). Third, the retrieved solution may not be comprehensible, i.e., the code segment might miss a succinct explanation. To address these three problems, we propose CROKAGE (Crowd Knowledge Answer Generator), a tool that takes the description of a programming task (the query) as input and delivers a comprehensible solution for the task. Our solutions contain not only relevant code examples but also their succinct explanations written by human developers. We evaluate and compare our approach against ten baselines, including the state-of-art. We show that CROKAGE outperforms the ten baselines in suggesting relevant solutions for 902 programming tasks (i.e., queries) of three popular programming languages: Java, Python and PHP. Furthermore, we use 24 programming tasks (queries) to evaluate our solutions with 29 developers and confirm that CROKAGE outperforms the state-of-art tool in terms of relevance of the suggested code examples, benefit of the code explanations and the overall solution quality (code + explanation).

show abstract

Section: Code Explanation Generationmentioning

confidence: 99%

“…Their approach combines the heuristics to rank the top most relevant comments for a source code. Chatterjee et al [Chatterjee et al 2017] develop a technique to extract descriptions associated with code segments from articles. Differently from Q&A websites, the code in articles is not delineated by markers.…”

Section: Code Explanation Generationmentioning

confidence: 99%

CROKAGE: Effective Solution Recommendation for Programming Tasks by Leveraging Crowd Knowledge

Silva

Maia

2021

Anais Estendidos Do XII Congresso Brasileiro De Software: Teoria E Prática (CBSoft Estendido 2021)

View full text Add to dashboard Cite

show abstract

“…Several early studies [2,16,43]- [48] propose automatic approaches to extract explanations to code. For this, they explore lexical properties usually in combination with strategies like clone detection [16,48], topics (like LDA) [43], word embeddings [2], machine learning [46] and deep learning [47]. Wong et al [16] propose a series of heuristics to match the code with natural language.…”

Section: B Code Explanation Generationmentioning

confidence: 99%

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

Silva

Roy

Rahman

et al. 2019

2019 IEEE/ACM 27th International Conference on Program Comprehension (ICPC)

View full text Add to dashboard Cite

Developers often search for relevant code examples on the web for their programming tasks. Unfortunately, they face two major problems. First, the search is impaired due to a lexical gap between their query (task description) and the information associated with the solution. Second, the retrieved solution may not be comprehensive, i.e., the code segment might miss a succinct explanation. These problems make the developers browse dozens of documents in order to synthesize an appropriate solution. To address these two problems, we propose CROKAGE (Crowd Knowledge Answer Generator), a tool that takes the description of a programming task (the query) and provides a comprehensive solution for the task. Our solutions contain not only relevant code examples but also their succinct explanations. Our proposed approach expands the task description with relevant API classes from Stack Overflow Q&A threads and then mitigates the lexical gap problems. Furthermore, we perform natural language processing on the top quality answers and then return such programming solutions containing code examples and code explanations unlike earlier studies. We evaluate our approach using 97 programming queries, of which 50% was used for training and 50% was used for testing, and show that it outperforms six baselines including the state-of-art by a statistically significant margin. Furthermore, our evaluation with 29 developers using 24 tasks (queries) confirms the superiority of CROKAGE over the state-of-art tool in terms of relevance of the suggested code examples, benefit of the code explanations and the overall solution quality (code + explanation).

show abstract

“…These papers focus on the main code commenting algorithms, and reflect the changing of research interests in the area of code commenting algorithms. Other neural network based algorithms [7], [9], [28], [51] Software Word Usage Model based algorithms [46], [47], [67], [69] Ontology-RDF based algorithms [62] Stereotype based algorithms [5], [49], [50] VSM/LSI based algorithms [25], [26], [57], [77], [86] Code clone detection based algorithms [82], [83] Automatic comment generation algorithms LDA based algorithms [52], [61]…”

Section: Trends Of the Development Of Code Commenting Techniquesmentioning

confidence: 99%

“…Stack Overflow. Accordingly, the specific tasks in this step vary from algorithm to algorithm [10,11,26] to some extent. For example, it is necessary for deep neural network based comment generation system [12,[27][28][29][30][31][32] to build high quality datasets (i.e.…”

Section: Challenges Of Automatic Code Commenting and Research Frameworkmentioning

confidence: 99%

A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques

et al. 2019

View full text Add to dashboard Cite

As an integral part of source code files, code comments help improve program readability and comprehension. However, developers sometimes do not comment on their program code adequately due to the incurred extra efforts, lack of relevant knowledge, unawareness of the importance of code commenting or some other factors. As a result, code comments can be inadequate, absent or even mismatched with source code, which affects the understanding, reusing and the maintenance of software. To solve these problems of code comments, researchers have been concerned with generating code comments automatically. In this work, we aim at conducting a survey of automatic code commenting researches. First, we generally analyze the challenges and research framework of automatic generation of program comments. Second, we present the classification of representative algorithms, the design principles, strengths and weaknesses of each category of algorithms. Meanwhile, we also provide an overview of the quality assessment of the generated comments. Finally, we summarize some future directions for advancing the techniques of automatic generation of code comments and the quality assessment of comments.Automatic code comment generation concerns the production of some textual descriptions of source code. The essential task is to translate the code written in programming languages into textual comments written in natural languages. Meanwhile, comments may describe not only the functions, but also the design intents of developers behind source code. In brief, automatic code commenting is to generate textual description written in natural languages automatically for source code by means of source code analysis, which can reveal the design intents, program logic, functionality of programs and the meanings of the related parameters, etc.

show abstract

Extracting Code Segments and Their Descriptions from Research Articles

Cited by 9 publications

References 20 publications

CROKAGE: Effective Solution Recommendation for Programming Tasks by Leveraging Crowd Knowledge

CROKAGE: Effective Solution Recommendation for Programming Tasks by Leveraging Crowd Knowledge

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques

Contact Info

Product

Resources

About