Haoruo Peng's Homepage

General Information

I am currently building Youlify, which provides billing service for private medical practices, with our own software and AI agents replacing human billers performing repetitive tasks.

I obtained my Ph.D. degree from UIUC, where I am most fortunate to work with my advisor Prof. Dan Roth in the Cognitive Computation Group. My research lies in the intersection of ML and NLP, and covers areas such as co-reference resolution, event extraction and co-reference, discourse parsing and semantic language modeling (script learning). Before that, I got my bachelor degree from Tsinghua University, where I worked with and learned a lot from Prof. Zhihua Zhang and Prof. Jun Zhu.

Education

Department of Computer Sciene, University of Illinois at Urbana-Champaign
Aug 2013 - Jul 2018
Ph.D. (advised by Prof. Dan Roth)
Thesis: Understanding Stories via Event Sequence Modeling [PDF]

Department of Computer Sciene and Technology, Tsinghua University
Aug 2009 - Jul 2013
B. Eng. in Computer Science

Selected Publications

Yangqiu Song, Shyam Upadhyay, Haoruo Peng, Stephen Mayhew, Dan Roth
Toward Any-language Zero-shot Topic Classification of Textual Documents [PDF]
Artificial Intelligence Journal, 2019
Qiang Ning, Hao Wu, Haoruo Peng, Dan Roth
Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource [PDF]
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL’18), 2018
Snigdha Chaturvedi, Haoruo Peng, Dan Roth
Story Comprehension for Predicting What Happens Next [PDF]
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP'17), 2017
Haoruo Peng, Ming-Wei Chang, Wen-tau Yih
Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision [PDF]
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP'17), 2017
Haoruo Peng, Snigdha Chaturvedi, Dan Roth
A Joint Model for Semantic Sequences: Frames, Entities, Sentiments [PDF]
In Proceedings of the SIGNLL Conference on Computational Natural Language Learning (CoNLL'17), 2017
Chao Zhang, Keyang Zhang, Quan Yuan, Haoruo Peng, Yu Zheng, Tim Hanratty, Shaowen Wang and Jiawei Han
Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning [PDF]
In Proceedings of the 26th International World Web Conference (WWW'17), 2017
Meng Zhang, Haoruo Peng, Yang Liu, Huanbo Luan, Maosong Sun
Bilingual Lexicon Induction From Non-Parallel Data With Minimal Supervision [PDF]
In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI'17), 2017
Haoruo Peng, Yangqiu Song, Dan Roth
Event Detection and Co-reference with Minimal Supervision [PDF] [Supplementary]
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP'16), 2016
Haoruo Peng, Dan Roth
Two Discourse Driven Language Models for Semantics [PDF]
In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL'16), 2016
Yangqiu Song, Shyam Upadhyay, Haoruo Peng, Dan Roth
Cross-lingual Dataless Classification for Many Languages [PDF]
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI'16), 2016
Haoruo Peng, Kai-Wei Chang, Dan Roth
A Joint Framework for Coreference Resolution and Mention Head Detection [PDF]
In Proceedings of the SIGNLL Conference on Computational Natural Language Learning (CoNLL’15), 2015
Haoruo Peng, Daniel Khashabi, Dan Roth
Solving Hard Coreference Problems [PDF]
In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL’15), 2015
Yifan Pi, Haoruo Peng, Shuchang Zhou, Edward Y. Chang, Zhihua Zhang
A Scalable Approach to Column-Based Low-Rank Matrix Approxiamtion [PDF]
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI'13), 2013
Haoruo Peng, Zhengyu Wang, Edward Y. Chang, Shuchang Zhou, Zhihua Zhang
Sublinear Algorithms for Penalized Logistic Regression in Masive Datasets [PDF]
In Proceedings of the European Conference on Machine Learning (ECML'12), 2012