Natural language elements (e.g., API comments, todo comments) form a substantial part of software repositories. While developers routinely use many natural language elements (e.g., todo comments) for communication, the semantic content of these elements is often neglected by software engineering techniques and tools. Additionally, as software evolves and development teams re-organize, these natural language elements are frequently forgotten, or just become outdated, imprecise and irrelevant. We envision several techniques, which combine natural language processing and program analysis, to help developers maintain their todo comments. Specifically, we propose techniques to synthesize code from comments, make comments executable, answer questions in comments, improve comment quality, and detect dangling comments.

PDF

In In Proceedings of the AAAI Workshop on NLP for Software Engineering, February 2018.

@inproceedings{nie:nlse18, title={Natural Language Processing and Program Analysis for Supporting Todo Comments as Software Evolves}, author={Pengyu Nie and Junyi Jessy Li and Sarfraz Khurshid and Raymond Mooney and Milos Gligoric}, booktitle={In Proceedings of the AAAI Workshop on NLP for Software Engineering}, month={February}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127683", year={2018} }