Luheng He


I am a research scientist at Google AI. I did my Ph.D. in the Department of Computer Science and Engineering at the University of Washington, advised by Prof. Luke Zettlemoyer. My research interests include natural language processing and computational linguistics.

[(slighly outdated) curriculum vitae] [Google scholar page]

Email: first_name at cs dot washington dot edu

Publications

Models for Semantics

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
Luheng He, Kenton Lee, Omer Levy, and Luke Zettlemoyer.
Annual Meeting of the Association for Computational Linguistics (ACL), 2018.
[code] [bibtex]

@inproceedings{he2018jointly,
title={Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling},
author={He, Luheng and Lee, Kenton and Levy, Omer and Zettlemoyer, Luke},
booktitle={Proceedings of the Annual Meeting of the Association for Computational Linguistics},
year={2018}
}

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
Yi Luan, Luheng He, Mari Ostendorf and Hannaneh Hajishirzi.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
[Yi's data and code] [bibtex]

@inproceedings{luan2018multi,
title={Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction},
author={Luan, Yi and He, Luheng and Ostendorf, Mari and Hajishirzi, Hannaneh},
booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
year={2018}
}

Higher-order Coreference Resolution with Coarse-to-fine Inference
Kenton Lee, Luheng He, and Luke Zettlemoyer.
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018.
[bibtex]

@inproceedings{lee2018higer,
title={Higher-order Coreference Resolution with Coarse-to-fine Inference},
author={Kenton Lee and Luheng He and Luke S. Zettlemoyer},
booktitle={Proceedings of the 2018 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year={2018}
}

End-to-end Neural Coreference Resolution
Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2017.
[Kenton's code] [demo] [bibtex]

@inproceedings{lee2017end,
title={End-to-end Neural Coreference Resolution},
author={Kenton Lee and Luheng He and Mike Lewis and Luke S. Zettlemoyer},
booktitle={Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
year={2017}
}

Deep Semantic Role Labeling: What Works and What's Next
Luheng He, Kenton Lee, Mike Lewis, and Luke Zettlemoyer.
Annual Meeting of the Association for Computational Linguistics (ACL), 2017.
[code] [slides (short)] [slides (long)] [bibtex]

@inproceedings{he2017deep,
title={Deep Semantic Role Labeling: What Works and What’s Next},
author={He, Luheng and Lee, Kenton and Lewis, Mike and Zettlemoyer, Luke},
booktitle={Proceedings of the Annual Meeting of the Association for Computational Linguistics},
year={2017}
}

Joint A∗ CCG Parsing and Semantic Role Labeling
Mike Lewis, Luheng He, and Luke Zettlemoyer.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015.
[Mike's code]

Natural-language-driven Annotations for Semantics

Large-Scale QA-SRL Parsing
Nicholas FitzGerald, Julian Michael, Luheng He, and Luke Zettlemoyer.
Annual Meeting of the Association for Computational Linguistics (ACL), 2018.
[QA-SRL Bank 2.0] [bibtex]

@inproceedings{fitzgerald2018large,
title={Large-Scale QA-SRL Parsing},
author={Nicholas FitzGerald and Julian Michael and Luheng He and Luke S. Zettlemoyer},
booktitle={Proceedings of the Annual Meeting of the Association for Computational Linguistics},
year={2018}
}

Crowdsourcing Question-Answer Meaning Representations
Julian Michael, Gabriel Stanovsky, Luheng He, Ido Dagan, and Luke Zettlemoyer.
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018.
[bibtex]

@inproceedings{michael2018crowdsourcing,
title={Crowdsourcing Question-Answer Meaning Representations},
author={Julian Michael and Gabriel Stanovsky and Luheng He and Ido Dagan and Luke S. Zettlemoyer},
booktitle={Proceedings of the 2018 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
year={2018}
}

Human-in-the-Loop Parsing
Luheng He, Julian Michael, Mike Lewis, and Luke Zettlemoyer.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016.
[code] [slides] [bibtex]

@inproceedings{he2016human,
title={Human-in-the-Loop Parsing},
author={He, Luheng and Michael, Julian and Lewis, Mike and Zettlemoyer, Luke}
booktitle={Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing},
year={2016}
}

Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language
Luheng He, Mike Lewis, and Luke Zettlemoyer.
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015.
[project homepage] [code] [slides]

Posterior Regularization

Multi-Label Learning with Posterior Regularization
Xi Victoria Lin, Sameer Singh, Luheng He, Ben Taskar and Luke Zettlemoyer
NIPS Workshop on Modern Machine Learning and Natural Language Processing, 2014.

Graph-Based Posterior Regularization for Semi-Supervised Structured Prediction
Luheng He, Jennifer Gillenwater, and Ben Taskar.
Conference on Computational Natural Language Learning (CoNLL), 2013.
[code] [supplement] [slides (for nwnlp 2014)]

Recommender Systems

Social Temporal Collaborative Ranking for Context Aware Movie Recommendation
Nathan N. Liu, Luheng He, and Qiang Yang.
ACM Transactions on Intelligent Systems and Technology (TIST), 2013.

Active Dual Collaborative Filtering with Both Item and Attribute Feedback
Luheng He, Nathan N. Liu, and Qiang Yang.
AAAI Conference on Artificial Intelligence, 2011.

Personal

Powerlifting and bouldering :)