Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
extensive code corpora, with the aim of developing intelligent tools to improve the quality …
Context-aware code change embedding for better patch correctness assessment
Despite the capability in successfully fixing more and more real-world bugs, existing
Automated Program Repair (APR) techniques are still challenged by the long-standing …
Automated Program Repair (APR) techniques are still challenged by the long-standing …
An exploratory literature study on sharing and energy use of language models for source code
Context: Large language models trained on source code can support a variety of software
development tasks, such as code recommendation and program repair. Large amounts of …
development tasks, such as code recommendation and program repair. Large amounts of …
On the significance of category prediction for code-comment synchronization
Software comments sometimes are not promptly updated in sync when the associated code
is changed. The inconsistency between code and comments may mislead the developers …
is changed. The inconsistency between code and comments may mislead the developers …
Cct5: A code-change-oriented pre-trained model
Software is constantly changing, requiring developers to perform several derived tasks in a
timely manner, such as writing a description for the intention of the code change, or …
timely manner, such as writing a description for the intention of the code change, or …
Practitioners' expectations on automated code comment generation
Good comments are invaluable assets to software projects, as they help developers
understand and maintain projects. However, due to some poor commenting practices …
understand and maintain projects. However, due to some poor commenting practices …
Ccrep: Learning code change representations via pre-trained code model and query back
Representing code changes as numeric feature vectors, ie, code change representations, is
usually an essential step to automate many software engineering tasks related to code …
usually an essential step to automate many software engineering tasks related to code …
A novel refactoring and semantic aware abstract syntax tree differencing tool and a benchmark for evaluating the accuracy of diff tools
P Alikhanifard, N Tsantalis - ACM Transactions on Software Engineering …, 2024 - dl.acm.org
Software undergoes constant changes to support new requirements, address bugs,
enhance performance, and ensure maintainability. Thus, developers spend a great portion …
enhance performance, and ensure maintainability. Thus, developers spend a great portion …
The devil is in the tails: How long-tailed code distributions impact large language models
Learning-based techniques, especially advanced Large Language Models (LLMs) for code,
have gained considerable popularity in various software engineering (SE) tasks. However …
have gained considerable popularity in various software engineering (SE) tasks. However …
Automating the removal of obsolete TODO comments
TODO comments are very widely used by software developers to describe their pending
tasks during software development. However, after performing the task developers …
tasks during software development. However, after performing the task developers …