Pinjia He

Postdoctoral Scholar

Department of Computer Science
ETH Zurich

Email: pinjia.he at inf.ethz.ch

General

Pinjia is a postdoctoral scholar in the Advanced Software Technologies (AST) Lab at ETH Zurich, mentored by Prof. Zhendong Su. He is working on software reliability for both intelligent software and traditional software. In his recent work, he has been focusing on automatically testing Machine Translation, part of which he found 1000+ translation errors from Google Translate and Bing Microsoft Translator.

Pinjia received his Ph.D. from The Chinese University of Hong Kong in 2018, supervised by Prof. Michael R. Lyu, where he worked on an end-to-end solution to intelligently manage and analyze logs for modern production systems (project LogPAI). LogPAI has received 2,000+ stars and 800+ forks and the datasets Loghub have been downloaded for 20,000+ times by 380+ organizations.

Research Interests

Software engineering; Robust NLP; Log analysis; SE for AI; AI for SE.

Selected Publications

Highlight: ICSE(3), ESEC/FSE(1), ASE(2), DSN(1), TDSC(1), TPDS(1)
[*corresponding author]

Pinjia He, Clara Meister, Zhendong Su
Testing Machine Translation via Referential Transparency
ICSE'21: Proceedings of the 43rd International Conference on Software Engineering, 2021.

Shashij Gupta, Pinjia He*, Clara Meister, Zhendong Su
Machine Translation Testing via Pathological Invariance
ESEC/FSE'20: Proceedings of the ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020.

Pinjia He, Clara Meister, Zhendong Su
Structure-Invariant Testing for Machine Translation
ICSE'20: Proceedings of the 42nd International Conference on Software Engineering, 2020.

Jinyang Liu, Jieming Zhu, Shilin He, Pinjia He*, Zibin Zheng, Michael R. Lyu
Logzip: Extracting Hidden Structures via Iterative Clustering for Log Compression
ASE'19: The 34th IEEE/ACM International Conference on Automated Software Engineering, 2019.

Pinjia He, Zhuangbin Chen, Shilin He, Michael R. Lyu
Characterizing the Natural Language Descriptions in Software Logging Statements
ASE'18: The 33rd IEEE/ACM International Conference on Automated Software Engineering, 2018.

Pinjia He, Jieming Zhu*, Shilin He, Jian Li, Michael R. Lyu
Towards Automated Log Parsing for Large-Scale Log Data Analysis
TDSC'18: IEEE Transactions on Dependable and Secure Computing, 2018.

Jieming Zhu, Pinjia He*, Zibin Zheng*, Michael R. Lyu
Online QoS Prediction for Runtime Service Adaptation via Adaptive Matrix Factorization
TPDS'17: IEEE Transactions on Parallel and Distributed Systems, 2017.

Pinjia He, Jieming Zhu, Zibin Zheng, Michael R. Lyu
Drain: An Online Log Parsing Approach with Fixed Depth Tree
ICWS'17: IEEE International Conference on Web Services, 2017.
Adopted by IBM Cloud: [blog post][IBM's code]

Pinjia He, Jieming Zhu, Shilin He, Jian Li, Michael R. Lyu
An Evaluation Study on Log Parsing and Its Use in Log Mining
DSN'16: The 46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2016.

Shilin He, Jieming Zhu, Pinjia He, Michael R. Lyu
Experience Report: System Log Analysis for Anomaly Detection
ISSRE'16: Proceedings of the 27th International Symposium on Software Reliability Engineering, 2016.
Most Influential Paper (26 selected in 30 years)

Jieming Zhu, Pinjia He, Qiang Fu, Hongyu Zhang, Michael R. Lyu, Dongmei Zhang
Learning to Log: Helping Developers Make Informed Logging Decisions
ICSE'15: Proceedings of the 37th International Conference on Software Engineering, 2015.

Jieming Zhu, Pinjia He, Zibin Zheng, Michael R. Lyu
Towards Online, Accurate, and Scalable QoS Prediction for Runtime Service Adaptation
ICDCS'14: The 34th International Conference on Distributed Computing Systems, 2014.