相关论文: Generating Commit Messages from Git Diffs

Corrective maintenance is crucial to ensure the quality of software, thereby improving reliability and user experience. In a version control system (VCS), developers write commit messages to document their changes and support later…

Synthetic text generation is challenging and has limited success. Recently, a new architecture, called Transformers, allow machine learning models to understand better sequential data, such as translation or summarization. BERT and GPT-2,…

Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text. In this work, we adapt a state-of-the-art neural machine translation model to…

When a Commit Message Generation (CMG) system is integrated into the IDEs and other products at JetBrains, we perform online evaluation based on user acceptance of the generated messages. However, performing online experiments with every…

Bug fixing is generally a manually-intensive task. However, recent work has proposed the idea of automated program repair, which aims to repair (at least a subset of) bugs in different ways such as code mutation, etc. Following in the same…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Data from software repositories have become an important foundation for the empirical study of software engineering processes. A recurring theme in the repository mining literature is the inference of developer networks capturing e.g.…

We present ComSum, a data set of 7 million commit messages for text summarization. When documenting commits, software code changes, both a message and its summary are posted. We gather and filter those to curate developers' work…

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural…

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…

Generative AI is changing the way that many disciplines are taught, including computer science. Researchers have shown that generative AI tools are capable of solving programming problems, writing extensive blocks of code, and explaining…

Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-generated correct code snippets. In this case, the…

Generative models have become adept at producing artifacts such as images, videos, and prose at human-like levels of proficiency. New generative techniques, such as unsupervised neural machine translation (NMT), have recently been applied…

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…

As AI coding agents become both primary producers and consumers of source code, the software industry faces an accelerating loss of institutional knowledge. Each commit captures a code diff but discards the reasoning behind it - the…

Commit messages in a version control system provide valuable information for developers regarding code changes in software systems. Commit messages can be the only source of information left for future developers describing what was changed…

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to…

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and…

The availability of open-source projects facilitates developers to contribute and collaborate on a wide range of projects. As a result, the developer community contributing to such open-source projects is also increasing. Many of the…

Data from software repositories have become an important foundation for the empirical study of software engineering processes. A recurring theme in the repository mining literature is the inference of developer networks capturing e.g.…