- Title
- NaturalCC: An Open-Source Toolkit for Code Intelligence
- Creator
- Wan, Yao; He, Yang; Yu, Philip S.; Bi, Zhangqian; Zhang, Jianguo; Sui, Yulei; Zhang, Hongyu; Hashimoto, Kazuma; Jin, Hai; Xu, Guandong; Xiong, Caiming
- Relation
- 2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion). Proceedings of 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) (Pittsburgh, PA 22-24 May, 2022) p. 149-153
- Publisher Link
- http://dx.doi.org/10.1145/3510454.3516863
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Resource Type
- conference paper
- Date
- 2022
- Description
- We present NaturalCC, an efficient and extensible open-source toolkit for machine-learning-based source code analysis (i.e., code intelligence). Using NaturalCC, researchers can conduct rapid prototyping, reproduce state-of-the-art models, and/or exercise their own algorithms. NaturalCC is built upon Fairseq and PyTorch, providing (1) a collection of code corpus with preprocessing scripts, (2) a modular and extensible framework that makes it easy to repro-duce and implement a code intelligence model, and (3) a benchmark of state-of-the-art models. Furthermore, we demonstrate the usability of our toolkit over a variety of tasks (e.g., code summarization, code retrieval, and code completion) through a graphical user interface. The website of this project is http://xcodemind.github.io, where the source code and demonstration video can be found.
- Subject
- code intelligence; deep learning; code representation; code embedding; open source; toolkit; benchmark
- Identifier
- http://hdl.handle.net/1959.13/1465807
- Identifier
- uon:47377
- Identifier
- ISBN:9781665495981
- Identifier
- ISSN:02705257
- Language
- eng
- Reviewed
- Hits: 4000
- Visitors: 3992
- Downloads: 2
Thumbnail | File | Description | Size | Format |
---|