Code summarization is the task of generating readable summaries that are semantically meaningful and can accurately describe the presumed task of a software. 1.

Tool for mining data from GitHub for code summarization tasks. Installation Follow these steps to run the tool.

CoDesc is a large dataset of 4.2m Java source code and parallel data of their description from code search, and code summarization studies. 4 PAPERS ...

Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software ...

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later.

CoDesc is a noise removed, large parallel dataset of source codes and corresponding natural language descriptions.

29 мая 2024 г. · For code summarization, the CodeSearchNet dataset [10] is used. This dataset contains programs in multiple languages: Python, Java, PHP ...

Extensive experiments on two large-scale datasets show that our approach can boost the effectiveness of five state-of-the-art code summarization approaches ...

Dataset for Code Summarization. Source publication. Dataset used for training PLM. Dataset for Code Summarization. Qualitative results from the MTurker studies.

4 апр. 2019 г. · Source Code Summarization is the task of writing short, natural language descriptions of source code.