Pengyu Nie
Ph.D. Candidate
The University of Texas at Austin
2501 Speedway C0803, EER 7E-010
Austin, TX 78712, USA
Email: pynie@utexas.edu
Pengyu Nie
Ph.D. Candidate
The University of Texas at Austin
2501 Speedway C0803, EER 7E-010
Austin, TX 78712, USA
Email: pynie@utexas.edu
Bio

I'm a Ph.D. student in the Department of Electrical and Computer Engineering at the University of Texas at Austin. I work with Prof. Milos Gligoric. My research interests focus on the fusion of software engineering, natural language processing, and programming languages. Specific topics include combining machine learning and code execution for software testing and verification, developing evolution-aware machine learning models for software maintenance, and designing domain specific languages for unifying multiple modalities of software.
I obtained my Bachelor's Degree at the University of Science and Technology of China, with majoring in both Physics and Computer Science.
Locate me on: GitHub (pengyunie), Google Scholar

I'm on the academic job market this year. Please contact me for opportunities!
Publications

14. Inline tests.
Yu Liu, Pengyu Nie, Owolabi Legunsen, and Milos Gligoric.
In International Conference on Automated Software Engineering
(ASE'22), to appear. October 2022.

13. CoditT5: Pretraining for source code and natural language editing.
Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Junyi Jessy Li, and Milos Gligoric.
In International Conference on Automated Software Engineering
(ASE'22), to appear. October 2022.

12. Impact of evaluation methodologies on code summarization.
Pengyu Nie, Jiyang Zhang, Junyi Jessy Li, Raymond J. Mooney, and Milos Gligoric.
In Annual Meeting of the Association for Computational Linguistics
(ACL'22), 4936-4960. May 2022.

11. Roosterize: Suggesting lemma names for Coq verification projects using deep learning.
Pengyu Nie, Karl Palmskog, Junyi Jessy Li, and Milos Gligoric.
In International Conference on Software Engineering, Tool Demonstrations Track
(ICSEDemo'21), 21-24. Virtual, May 2021.

10. Leveraging class hierarchy for code comprehension.
Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Junyi Jessy Li, Raymond J. Mooney, and Milos Gligoric.
In Workshop on Computer Assisted Programming
(CAP'20). Virtual, December 2020.

9. Unifying execution of imperative generators and declarative specifications. [slides] [talk]
Pengyu Nie, Marinela Parovic, Zhiqiang Zang, Sarfraz Khurshid, Aleksandar Milicevic, and Milos Gligoric.
In Conference on Object-Oriented Programming Systems, Languages and Applications
(OOPSLA'20), 217:1-217:26. Chicago, Illinois, USA, November 2020.

8. On the naturalness of hardware descriptions. [slides] [talk]
Jaeseong Lee, Pengyu Nie, Junyi Jessy Li, and Milos Gligoric.
In Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
(ESEC/FSE'20), 530-542. Sacramento, California, USA, November 2020.

7. Learning to format Coq code using language models. [slides]
Pengyu Nie, Karl Palmskog, Junyi Jessy Li, and Milos Gligoric.
In The Coq Workshop
(Coq'20). Paris, France, July 2020.

6. Debugging the performance of Maven's test isolation: Experience report. [slides]
Pengyu Nie, Ahmet Celik, Matthew Coley, Aleksandar Milicevic, Jonathan Bell, and Milos Gligoric.
In International Symposium on Software Testing and Analysis
(ISSTA'20), 249-259. Los Angeles, California, USA, July 2020.

5. Learning to update natural language comments based on code changes.
Sheena Panthaplackel, Pengyu Nie, Milos Gligoric, Junyi Jessy Li, and Raymond J. Mooney.
In Annual Meeting of the Association for Computational Linguistics
(ACL'20), 1853-1868. Seattle, Washington, USA, July 2020.

4. Deep generation of Coq lemma names using elaborated terms. [slides] [talk]
Pengyu Nie, Karl Palmskog, Junyi Jessy Li, and Milos Gligoric.
In International Joint Conference on Automated Reasoning
(IJCAR'20), 97-118. Paris, France, June 2020.

3. Design, implementation, and application of GPU-based Java bytecode interpreters.
Ahmet Celik, Pengyu Nie, Christopher J. Rossbach, and Milos Gligoric.
In Conference on Object-Oriented Programming Systems, Languages and Applications
(OOPSLA'19), 177:1-177:28. Athens, Greece, October 2019.

2. A framework for writing trigger-action todo comments in executable format. [slides]
Pengyu Nie, Rishabh Rai, Junyi Jessy Li, Sarfraz Khurshid, Raymond J. Mooney, and Milos Gligoric.
In Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
(ESEC/FSE'19), 385-396. Tallinn, Estonia, August 2019.
This paper won an ACM SIGSOFT Distinguished Paper Award.

1. Natural language processing and program analysis for supporting todo comments as software evolves.
Pengyu Nie, Junyi Jessy Li, Sarfraz Khurshid, Raymond J. Mooney, and Milos Gligoric.
In Workshop on Natural Language Processing for Software Engineering
(NL4SE'18), 775-778. New Orleans, Louisiana, USA, February 2018. Long presentation.

Service

2022: Reviewer of TSE. External reviewer of ICSE
2021: PC member of AAAI, NLP4Prog, AIST. External reviewer of ASE
2020: External reviewer of ICSE, ISSTA, COLING, ISSRE.
2019: External reviewer of ICSE, ISSTA, IJCAI.
2018: External reviewer of ASE, ESEC/FSE.

Co-organizer of the NLP+Programming Reading Group at the University of Texas at Austin.

Co-organizer of the Joint UT-Cornell Software Engineering Seminar.