Retrieval on source code: a neural code search

Sachdev, Saksham; Li, Hongyu; Luan, Sifei; Kim, Seohyun; Sen, Koushik; Chandra, Satish

doi:10.1145/3211346.3211353

Cited by 153 publications

(146 citation statements)

References 9 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…In the third experiment for RQ3, we use the ranking position of the original matched code in search results as the basis for Frank, Recall@k, and MRR benchmark evaluation. However, in some related work, the search results are inspected by participants who spend time and effort labeling them based on relevance to the query. We believe the threat of lacking of manual evaluation is not significant as the machine evaluation is more convincing.…”

Section: Discussionmentioning

confidence: 99%

Unsupervised software repositories mining and its application to code search

Peng

Yihan

et al. 2019

Softw Pract Exp

View full text Add to dashboard Cite

Software repositories are crucial resources for many software tasks, including code retrieval and annotation. Programming forums provide questions and answers (Q&A) from software developers, containing abundant code-description posts for exchanging knowledge about programming issues. However, most posts provide personal opinions of users that are often not adequately confirmed or outdated. Mining software repositories in such open and unrestricted forums is challenging. Since the posts can be arbitrary and noisy, it is difficult to get unified labels for supervised noise elimination. Different from existing mining approaches, this paper proposes Code-Description Mining Framework (CodeMF), an unsupervised framework to eliminate noisy posts and extract high quality software repositories from programming forums.CodeMF treats all social features of the posts as discrete-time signals for kernel principal component analysis and further performs wavelet transform feature fusion to find the delicate changes (noises in temporal signals). We conduct comprehensive experiments on StackOverflow. Experimental results demonstrate that CodeMF can effectively reduce running time and improve precision via mining high-quality software repositories for various programming languages, especially for the large-scale codebases. To further illustrate the effect of CodeMF applied in software tasks, we introduce it to improve the performance of query-expansion code search. Meanwhile, for SQL and C# programs, compared to the state-of-the-art query-expansion method QECK, the improvement of QECK CodeMF is 2% and 6% on Recall@10, and 4% and 14% on mean reciprocal rank, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Unsupervised software repositories mining and its application to code search

Peng

Yihan

et al. 2019

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…Recent works from both academia and industry have explored the realm of code search. NCS [26] presented a simple yet effective unsupervised model. CODEnn [15] and SCS [19] provided a deep learning approach by using sophisticated neural networks.…”

Section: Related Workmentioning

confidence: 99%

“…Proprietary code repositories in particular pose a challenge, as developers can no longer rely on public sources such as Google or Stack Overflow for assistance, as these may not capture the required organization-specific API and library usage. However, recent works from both academia and industry [15,19,21,26] have taken steps towards enabling more advanced code search using deep learning. We call such methods neural code search.…”

mentioning

confidence: 99%

When deep learning met code search

Cambronero

Kim

et al. 2019

Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of

Self Cite

183

146

View full text Add to dashboard Cite

There have been multiple recent proposals on using deep neural networks for code search using natural language. Common across these proposals is the idea of embedding code and natural language queries, into real vectors and then using vector distance to approximate semantic correlation between code and the query. Multiple approaches exist for learning these embeddings [15,19,24,26], including unsupervised techniques, which rely only on a corpus of code examples, and supervised techniques, which use an aligned corpus of paired code and natural language descriptions. The goal of this supervision is to produce embeddings that are more similar for a query and the corresponding desired code snippet.Clearly, there are choices in whether to use supervised techniques at all, and if one does, what sort of network and training to use for supervision. This paper is the first to evaluate these choices systematically. To this end, we assembled implementations of stateof-the-art techniques to run on a common platform, training and evaluation corpora. To explore the design space in network complexity, we also introduced a new design point that is a minimal supervision extension to an existing unsupervised technique.Our evaluation shows that: 1. adding supervision to an existing unsupervised technique can improve performance, though not necessarily by much; 2. simple networks for supervision can be more effective that more sophisticated sequence-based networks for code search; 3. while it is common to use docstrings to carry out supervision, there is a sizeable gap between the effectiveness of docstrings and a more query-appropriate supervision corpus.

show abstract

“…Many efforts have been made to improve keyword-based code search [Bajracharya et al 2006;Chan et al 2012;Martie et al 2015;McMillan et al 2012;Sachdev et al 2018]. CodeGenie [Lemos et al 2007] uses test cases to search and reuse source code; SNIFF [Chatterjee et al 2009] works by inlining API documentation in its code corpus.…”

Section: Related Workmentioning

confidence: 99%

Aroma: code recommendation via structural code search

Luan

Yang

Barnaby

et al. 2019

Proc. ACM Program. Lang.

Self Cite

119

View full text Add to dashboard Cite

Programmers often write code that has similarity to existing code written somewhere. A tool that could help programmers to search such similar code would be immensely useful. Such a tool could help programmers to extend partially written code snippets to completely implement necessary functionality, help to discover extensions to the partial code which are commonly included by other programmers, help to cross-check against similar code written by other programmers, or help to add extra code which would fix common mistakes and errors. We propose Aroma, a tool and technique for code recommendation via structural code search. Aroma indexes a huge code corpus including thousands of open-source projects, takes a partial code snippet as input, searches the corpus for method bodies containing the partial code snippet, and clusters and intersects the results of the search to recommend a small set of succinct code snippets which both contain the query snippet and appear as part of several methods in the corpus. We evaluated Aroma on 2000 randomly selected queries created from the corpus, as well as 64 queries derived from code snippets obtained from Stack Overflow, a popular website for discussing code. We implemented Aroma for 4 different languages, and developed an IDE plugin for Aroma. Furthermore, we conducted a study where we asked 12 programmers to complete programming tasks using Aroma, and collected their feedback. Our results indicate that Aroma is capable of retrieving and recommending relevant code snippets efficiently. few code snippets shown in Listings 2, 3, which demonstrate how to configure the decoder to use less memory, and how to handle potential runtime exceptions, respectively. We call this the code recommendation problem. InputStream input = manager.open(fileName); Bitmap image = BitmapFactory.decodeStream(input); Listing 1. Suppose an Android programmer writes this code to decode a bitmap. final BitmapFactory.Options options = new BitmapFactory.Options(); options.inSampleSize = 2; Bitmap bmp = BitmapFactory.decodeStream(is, null, options); Listing 2. A recommended code snippet that shows how to configure the decoder to use less memory. Recommended lines are highlighted. 1 try { InputStream is = am.open(fileName); image = BitmapFactory.decodeStream(is); is.close(); } catch (IOException e) { // ... } Listing 3. Another recommended code snippet that shows how to properly close the input stream and handle any potential IOException. Recommended lines are highlighted. 2

show abstract

Retrieval on source code: a neural code search

Cited by 153 publications

References 9 publications

Unsupervised software repositories mining and its application to code search

Unsupervised software repositories mining and its application to code search

When deep learning met code search

Aroma: code recommendation via structural code search

Contact Info

Product

Resources

About