Deep Code Search

By Xiaodong Gu, Hongyu Zhang, Sunghun Kim. 2018

687 citations recorded by the source corpus.

Subfields: Information Systems, Information Systems and Management, Information Retrieval & Search, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Information Systems and Management

In Information Retrieval & Search

In Code Generation & Program Synthesis

Citations in the corpus

CodeBERT: A Pre-Trained Model for Programming and Natural Languages (2020, background): “The first four rows are reported by Husain et al. (2019), which are joint embeddings of NL and PL (Gu et al., 2018; Mitra et al., 2018).”
CodeSearchNet Challenge: Evaluating the State of Semantic Code Search (2019, methodology): “Following earlier work [11, 20], we use joint embeddings of code and queries to implement a neural search system.”
IntelliCode compose: code generation using transformer (2020, background): “Some of the early applications of machine learning of source code include code search [1, 2], bug detection and localization [3], program synthesis [4], code summarization [5] and code completion [6–10].”
DOBF: A Deobfuscation Pre-Training Objective for Programming Languages (2021, methodology): “Machine learning is frequently used on tasks involving programming languages, including code completion [28, 33, 35, 42], bug detection and code repair [15, 38, 46], code summarization [8, 25], clone detection [2, 47, 48], code search [13, 23] and code translation [14, 41].”
An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation (2018, background): “Some examples of recent models that can be used in a number of software engineering tasks include: code completion [67, 91], defect prediction [84], bug localization [39], clone detection [80, 90], code search [23], learning Application Programming Interface (API) sequences [24], recommending method”
CODIT: Code Editing With Tree-Based Neural Models (2018, methodology): “Applying ML to source code has received increasing attention in recent years [26] across many applications such as code completion [11], [31], bug prediction [57], [58], [59], clone detection [60], code search [61], etc.”
Semantic code search via equational reasoning (2020, methodology): “Beyond these 4 tools which were strong candidates for a meaningful comparison, we also substantially investigated 3 other tools (Oreo [72], DCS [18], and Alice [76]), but for each found that the problems addressed were too different, the benchmarks were a mutual poor fit, and/or any experiment proto”
Learning to Spot and Refactor Inconsistent Method Names (2019, background): “Recently, a number of studies [45]–[51] have provided empirical evidence”
Retrieval-based Neural Source Code Summarization (2020, methodology): “Similar to [16], we apply a global max pooling operation over the vector sequence to obtain the semantic representation rc ∈ R1×2k as follows:”
CoCoNuT: combining context-aware neural translation models using ensemble for program repair (2020, methodology): “Deep Learning in Software Engineering: The software engineering community had applied deep learning to perform various tasks such as defects prediction [40, 79, 81], source code representation [6, 7, 66, 80], source code summarization [4, 22] source code modeling [5, 11, 26, 83], code clone detectio”
CoSQA: 20,000+ Web Queries for Code Search and Question Answering (2021, background): “A number of open-sourced datasets with a large amount of text-code pairs have been proposed for the purposes of code search (Husain et al., 2019; Gu et al., 2018; Nie et al., 2016) and code question answering (Yao et al.”
Neural Detection of Semantic Code Clones Via Tree-Based Convolution (2019, methodology): “A common technique that can mitigate the challenge is to separate a token into a sequence of tokens according to camel case [29].”
On Learning Meaningful Code Changes Via Neural Machine Translation (2019, methodology): “This implementation uses NNs and natural language to embed code snippets with natural language descriptions into a high-dimensional vector space, helping developers locate source code based on natural language queries [40].”
Structured Neural Summarization (2018, methodology): “on et al. (2018b;a)extractandencodepathsfromthesyntaxtreeofaprogram, setting the state of the art in accuracy on method naming. Linking text to code can have useful applications, such as code search (Gu et al., 2018), traceability (Guo et al., 2017), and detection of redundant method comments (Louis”