相关论文: CommitBART: A Large Pre-trained Model for GitHub C…

Bots are frequently used in Github repositories to automate repetitive activities that are part of the distributed software development process. They communicate with human actors through comments. While detecting their presence is…

Generative pre-trained transformer (GPT) models have revolutionized the field of natural language processing (NLP) with remarkable performance in various tasks and also extend their power to multimodal domains. Despite their success, large…

We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code…

AI-agents help developers in different coding tasks, such as developing new features, fixing bugs, and reviewing code. Developers can write a Github issue and assign it to an AI-agent like Copilot for implementation. Based on the issue and…

GitHub's issue reports provide developers with valuable information that is essential to the evolution of a software development project. Contributors can use these reports to perform software engineering tasks like submitting bugs,…

Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content. We show that fine-tuning pre-trained language (GPT-2) and sequence-to-sequence (BART) models boosts content preservation, and…

Intelligent and reliable task planning is a core capability for generalized robotics, requiring a descriptive domain representation that sufficiently models all object and state information for the scene. We present CLIMB, a continual…

Continuous Integration (CI) is a cornerstone of modern collaborative software development, and numerous CI platforms are available. Differences in maintenance overhead, reliability, and integration depth with code-hosting platforms make…

Software engineering research has always being concerned with the improvement of code completion approaches, which suggest the next tokens a developer will likely type while coding. The release of GitHub Copilot constitutes a big step…

Commit messages are crucial for documenting software changes, aiding in program comprehension and maintenance. However, creating effective commit messages is often overlooked by developers due to time constraints and varying levels of…

Background: Open source software has an increasing importance in modern software development. However, there is also a growing concern on the sustainability of such projects, which are usually managed by a small number of developers,…

Many Transformer-based pre-trained models for code have been developed and applied to code-related tasks. In this paper, we review the existing literature, examine the suitability of model architectures for different tasks, and look at the…

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 code-related tasks. Despite their success, most current methods…

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

This paper aims to evaluate GitHub Copilot's generated code quality based on the LeetCode problem set using a custom automated framework. We evaluate the results of Copilot for 4 programming languages: Java, C++, Python3 and Rust. We aim to…

Pre-trained language models have recently emerged as a powerful tool for fine-tuning a variety of language tasks. Ideally, when models are pre-trained on large amount of data, they are expected to gain implicit knowledge. In this paper, we…

Much of software-engineering research relies on the naturalness of code, the fact that code, in small code snippets, is repetitive and can be predicted using statistical language models like n-gram. Although powerful, training such models…

In software development there is a constant pressure to produce code faster and faster without compromising on quality. New tools supporting developers are created in response to this demand. Currently a new generation of such solutions is…

Lehman's Laws teach us that a software system will become progressively less satisfying to its users over time, unless it is continually adapted to meet new needs. Understanding software maintenance can potentially relieve many of the pains…

Studies on grammatical error correction (GEC) have reported the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining for GEC because of the size of the…