A survey on deep learning for software engineering
In 2006, Geoffrey Hinton proposed the concept of training “Deep Neural Networks (DNNs)”
and an improved model training method to break the bottleneck of neural network …
and an improved model training method to break the bottleneck of neural network …
Natural language generation and understanding of big code for AI-assisted programming: A review
MF Wong, S Guo, CN Hang, SW Ho, CW Tan - Entropy, 2023 - mdpi.com
This paper provides a comprehensive review of the literature concerning the utilization of
Natural Language Processing (NLP) techniques, with a particular focus on transformer …
Natural Language Processing (NLP) techniques, with a particular focus on transformer …
Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models
Recent advances in Large Language Models (LLM) have made automatic code generation
possible for real-world programming tasks in general-purpose programming languages …
possible for real-world programming tasks in general-purpose programming languages …
Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation
Pre-trained models for Natural Languages (NL) like BERT and GPT have been recently
shown to transfer well to Programming Languages (PL) and largely benefit a broad set of …
shown to transfer well to Programming Languages (PL) and largely benefit a broad set of …
Large language models for software engineering: Survey and open problems
This paper provides a survey of the emerging area of Large Language Models (LLMs) for
Software Engineering (SE). It also sets out open research challenges for the application of …
Software Engineering (SE). It also sets out open research challenges for the application of …
Unified pre-training for program understanding and generation
Code summarization and generation empower conversion between programming language
(PL) and natural language (NL), while code translation avails the migration of legacy code …
(PL) and natural language (NL), while code translation avails the migration of legacy code …
Codexglue: A machine learning benchmark dataset for code understanding and generation
Benchmark datasets have a significant impact on accelerating research in programming
language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster …
language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster …
Examining zero-shot vulnerability repair with large language models
Human developers can produce code with cybersecurity bugs. Can emerging 'smart'code
completion tools help repair those bugs? In this work, we examine the use of large language …
completion tools help repair those bugs? In this work, we examine the use of large language …
Graphcodebert: Pre-training code representations with data flow
Pre-trained models for programming language have achieved dramatic empirical
improvements on a variety of code-related tasks such as code search, code completion …
improvements on a variety of code-related tasks such as code search, code completion …
Cure: Code-aware neural machine translation for automatic program repair
Automatic program repair (APR) is crucial to improve software reliability. Recently, neural
machine translation (NMT) techniques have been used to automatically fix software bugs …
machine translation (NMT) techniques have been used to automatically fix software bugs …