Spotting familiar code snippet structures for program comprehension

Vinayakarao, Venkatesh

doi:10.1145/2786805.2807560

Cited by 4 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have been conducted on solving the software engineering tasks by leveraging the discussions on Stack Overflow, for example, mining source code description [54], extracting cookbooks for APIs [12], helping developers debugging their code [11], assisting software comprehension and development [36], [46], [37], locating method definitions on Stack Overflow [55], and so on. We focus on the studies about recommending Q&A pairs on Stack Overflow.…”

Section: Qanda Pairs Recommendationmentioning

confidence: 99%

Query Expansion Based on Crowd Knowledge for Code Search

Nie

Jiang

Zhang

et al. 2016

IEEE Trans. Serv. Comput.

134

105

View full text Add to dashboard Cite

As code search is a frequent developer activity in software development practices, improving the performance of code search is a critical task. In the text retrieval based search techniques employed in the code search, the term mismatch problem is a critical language issue for retrieval effectiveness. By reformulating the queries, query expansion provides effective ways to solve the term mismatch problem. In this paper, we propose Query Expansion based on Crowd Knowledge (QECK), a novel technique to improve the performance of code search algorithms. QECK identifies software-specific expansion words from the high quality pseudo relevance feedback question and answer pairs on Stack Overflow to automatically generate the expansion queries. Furthermore, we incorporate QECK in the classic Rocchio's model, and propose QECK based code search method QECKRocchio. We conduct three experiments to evaluate our QECK technique and investigate QECKRocchio in a large-scale corpus containing real-world code snippets and a question and answer pair collection. The results show that QECK improves the performance of three code search algorithms by up to 64 percent in Precision, and 35 percent in NDCG. Meanwhile, compared with the state-of-the-art query expansion method, the improvement of QECK Rocchio is 22 percent in Precision, and 16 percent in NDCG.Comment: 14 pages, 5 figures, IEEE Transactions on Services Computing, 201

show abstract

Section: Qanda Pairs Recommendationmentioning

confidence: 99%

Query Expansion Based on Crowd Knowledge for Code Search

Nie

Jiang

Zhang

et al. 2016

IEEE Trans. Serv. Comput.

134

105

View full text Add to dashboard Cite

show abstract

“…Based on the search information of question-and-answer information, the query statement is extended. Although the expansion direction is different from Vinayakarao's method [8], they both have good effects. Lu et al [17] proposed a code search method based on a lexical network.…”

Section: Code Search Based On Information Retrievalmentioning

confidence: 91%

“…The search results are obtained by measuring the distance between vectors. Vinayakarao et al [8] also have similar methods. The difference is that they use Stack Overflow, a developer Q&A community, to gather information.…”

Section: Code Search Based On Information Retrievalmentioning

confidence: 98%

“…Nie et al [16] proposed a code search method that enhances the search text with question-and-answer information. This method combines the methods of Vinayakarao [8] and Lemo [15]. Based on the search information of question-and-answer information, the query statement is extended.…”

Section: Code Search Based On Information Retrievalmentioning

confidence: 99%

“…Although a lot of code search techniques are proposed in recent years, there are still some problems in this area [6,7]: (1) The existing code search technology is not comprehensive in the representation of code, most of them only pay attention to the information of the code itself and ignore the code annotation information; (2) In terms of code annotation information, the existing search technology simply regards all annotation information as equally weighted information, ignoring the specificity of code annotation; (3) The search content of the existing code search technology is simple, and there is no better strategy in the face of more complex search conditions [8,9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Boosting Code Search with Structural Code Annotation

Kong

Chen

et al. 2022

Electronics

View full text Add to dashboard Cite

Code search is a process that takes a given query as input and retrieves relevant code snippets from a code base. The relationship between query and code is commonly built on code annotation, which is extracted from code comments or other documents. The current code search studies approximately treat code annotation as a common natural language, regardless of its hidden structural information. To address the information loss, this work proposes a code annotation model to extract features from five perspectives, and further conduct a code search engine, i.e., CodeHunter. CodeHunter is evaluated on a dataset of 7 million code snippets and query descriptions. The experimental results show that CodeHunter obtains more effective results than Lucene and DeepCS. And we also prove that the effectiveness comes from the rich features and search models, CodeHunter can work well with different sizes of query descriptions.

show abstract

Modeling Source Code to Support Retrieval-Based Applications

Vinayakarao

2017

Proceedings of the Tenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Spotting familiar code snippet structures for program comprehension

Cited by 4 publications

References 10 publications

Query Expansion Based on Crowd Knowledge for Code Search

Query Expansion Based on Crowd Knowledge for Code Search

Boosting Code Search with Structural Code Annotation

Modeling Source Code to Support Retrieval-Based Applications

Contact Info

Product

Resources

About