Department of Computer Science

Machine Learning Research Group

University of Texas at Austin Artificial Intelligence Lab

Publications: Natural Language for Software Engineering

The ability to translate instructions expressed in natural language directly to executable software is of considerable use in many applications such as personal assistants, as well as in making computers and automated systems more accessible to users unfamiliar with computer programming. Our work has focused on using semantic parsing and dialog to interpret English "if this then that" (IFTTT) instructions and using the evolution of comments and code in open source software repositories and a combination of NLP and program analysis methods to automate various software engineering tasks.
  1. Associating Natural Language Comment and Source Code Entities
    [Details] [PDF]
    Sheena Panthaplackel, Milos Gligoric, Raymond J. Mooney and Junyi Jessy Li
    To Appear In The AAAI Conference on Artificial Intelligence (AAAI), 2020.
  2. A Framework for Writing Trigger - Action Todo Comments in Executable Format
    [Details] [PDF] [Slides (PPT)]
    Pengyu Nie, Rishabh Rai, Junyi Jessy Li, Sarfraz Khurshid, Raymond J. Mooney, Milos Gligoric
    In Proceedings of the ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), Tallinn, Estonia, August 2019. Distinguished Paper Award.
  3. Natural Language Processing and Program Analysis for Supporting Todo Comments as Software Evolves
    [Details] [PDF]
    Pengyu Nie, Junyi Jessy Li, Sarfraz Khurshid, Raymond Mooney, Milos Gligoric
    In In Proceedings of the AAAI Workshop on NLP for Software Engineering, February 2018.
  4. Dialog for Language to Code
    [Details] [PDF] [Poster]
    Shobhit Chaurasia and Raymond J. Mooney
    In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP-17), 175-180, Taipei, Taiwan, November 2017.
  5. Dialog for Natural Language to Code
    [Details] [PDF]
    Shobhit Chaurasia
    2017. Masters Thesis, Computer Science Department, University of Texas at Austin.
  6. Improved Semantic Parsers For If-Then Statements
    [Details] [PDF]
    I. Beltagy and Chris Quirk
    To Appear In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-16), Berlin, Germany, 2016.
  7. Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
    [Details] [PDF] [Poster]
    Chris Quirk and Raymond Mooney and Michel Galley
    In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL-15), 878--888, Beijing, China, July 2015.