Litcius/Paper detail

Improving Code Search with Co-Attentive Representation Learning

Jianhang Shuai, Ling Xu, Chao Liu, Meng Yan, Xin Xia, Yan Lei

2020124 citationsDOI

Abstract

Searching and reusing existing code from a large-scale codebase, e.g, GitHub, can help developers complete a programming task efficiently. Recently, Gu et al. proposed a deep learning-based model (i.e., DeepCS), which significantly outperformed prior models. The DeepCS embedded codebase and natural language queries into vectors by two LSTM (long and short-term memory) models separately, and returned developers the code with higher similarity to a code search query. However, such embedding method learned two isolated representations for code and query but ignored their internal semantic correlations. As a result, the learned isolated representations of code and query may limit the effectiveness of code search.

Topics & Concepts

CodebaseComputer scienceCode (set theory)EmbeddingCode reuseProgramming languageTask (project management)Web search queryArtificial intelligenceCode reviewInformation retrievalTheoretical computer scienceNatural language processingSource codeStatic program analysisSoftware developmentSoftwareSearch engineSet (abstract data type)EconomicsManagementSoftware Engineering ResearchTopic ModelingScientific Computing and Data Management
Improving Code Search with Co-Attentive Representation Learning | Litcius