My Photo

Hongming Zhang

Biography

I am currently a research scholar at University of Pennsylvania, working with Prof. Prof. Dan Roth. In 2021, I got my Ph.D. degree from HKUST, supervised by Prof. Yangqiu Song. Before that, I received my MPhil. degree from the TLE program, HKUST in 2018 and B.E.degree from the ECE department, HKUST in 2016. My research interest is primarily on commonsense reasoning and multi-modal event understanding. Specifically, I aim at building a large-scale eventuality-centric knowledge graph to connect different modalities and help machines understand the event-centric commonsense. You can find me at hzhangal [AT] cse.ust.hk or learn more about me with my Google Scholar, Github, and CV (Aug, 2021).

Current Research Focus

  • Commonsense Reasoning
  • Open-domain Event Understanding
  • Selectional Preference
  • Coreference Resolution

News

  • 08/2021: Four papers were accepted to EMNLP 2021 main conference. Topics include commonsense, coreference, and event information extraction.
  • 08/2021: One paper about pragmatics was accepted to AKBC 2021.
  • 08/2021: Invited to serve as the PC of IJCAI 2022 and AAAI 2022.
  • 06/2021: I successfully defend my Ph.D. thesis.
  • 05/2021: Invited to give a talk at MILA AI seminar about commonsense and eventualities.
  • 05/2021: Invited to give a talk at USC-ISI AI seminar about commonsense and eventualities.
  • 05/2021: Three papers were accepted to ACL 2021 (one main conference; two findings). Topics include zero-shot event extraction and argument persuasion.
  • 04/2021: Invited to serve as the PC of EMNLP 2021.
  • 04/2021: A paper about discovering the causal relation between daily events from videos has been accepted by the "Causality in Vision" workshop at CVPR 2021.
  • 01/2021: A paper about transfering ASER knowledge into complex commonsense has been accepted to WWW 2021.
  • 01/2021: A paper about coreference has been accepted to EACL 2021.
  • 12/2020: Invited to give a talk about commonsense at the Tsinghua AI Time Forum.
  • 12/2020: Invited to serve as the PC of ACL 2021.
  • 12/2020: Our tutorial proposal about event-centric NLP has been accepted by ACL 2021.
  • 11/2020: Invited to serve as the Senior PC of IJCAI 2021.

Talks

  • 2021 July: Tencent. Towards Commonsense Reasoning from the Angle of Eventualities.
  • 2021 June: Mila AI Seminar. Towards Commonsense Reasoning from the Angle of Eventualities.
  • 2021 April: Amazon Search. Commonsense Reasoning from the Angle of Eventualities. [Slides]
  • 2021 February: AAAI 2021 Tutorial (with Muhao, Qiang, Manling, Heng, and Dan). Event-centric Natural Language Understanding. [Slides]
  • 2021 January: Tsinghua AI Time Forum. The Transferability from Linguistic Knowledge to Commonsense Knowledge. [Slides]
  • 2020 November: Google. Analogous Process Structure Induction for Sub-event Sequence Prediction. [Slides]
  • 2020 September: NLP with Friends. Commonsense Reasoning from the Angle of Eventualities. [Slides] [Video]
  • 2019 October: Microsoft Research Asia (MSRA). Event-centric Commonsense Reasoning with Structured Knowledge. [Slides]
[Selected Publications by Topics] [Full Publications by Year]

Commonsense Reasoning

  • Hongming Zhang*, Xin Liu*, Haojie Pan*, Yangqiu Song, and Cane Wing-Ki Leung. ASER: A Large-scale Eventuality Knowledge Graph. The Web Conference (WWW). 2020. [PAPER] [CODE & DATA] [PPT]
  • Hongming Zhang, Daniel Khashabi, Yangqiu Song, and Dan Roth. TransOMCS: From Linguistic Graphs to Commonsense Knowledge. International Joint Conference on Artificial Intelligence (IJCAI). 2020. [PAPER] [CODE & DATA] [PPT]
  • Hongming Zhang*, Xinran Zhao*, and Yangqiu Song. WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge. Annual Meeting of the Association for Computational Linguistics (ACL). 2020. [PAPER] [CODE & DATA] [PPT]
  • Tianqing Fang, Hongming Zhang, Weiqi Wang, Yangqiu Song, and Bin He. DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge. The Web Conference (WWW). 2021. [PAPER] [CODE & DATA]
  • Changlong Yu*, Hongming Zhang*, Yangqiu Song, and Wilfred Ng. CoCoLM: COmplex COmmonsense Enhanced Language Model. ArXiv Preprint. 2020. [PAPER] [CODE & DATA]

Event Understanding

  • Hongming Zhang, Muhao Chen, Haoyu Wang, Yangqiu Song, and Dan Roth. Analogous Process Structure Induction for Sub-event Sequence Prediction. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. [PAPER] [CODE & DATA] [PPT]
  • Muhao Chen, Hongming Zhang, Haoyu Wang, and Dan Roth. What Are You Trying to Do? Semantic Typing of Event Processes. The SIGNLL Conference on Computational Natural Language Learning (CoNLL). 2020. [PAPER] [CODE & DATA] (Best Paper Nomination)
  • Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, and Dan Roth. Learning Contextual Causality from Time-consecutive Images. Causality in Vision workshop at CVPR 2021. [PAPER] [CODE & DATA]

Information Extraction

  • Hongming Zhang, Haoyu Wang, and Dan Roth. Zero-shot Label-Aware Event Trigger and Argument Classification. Annual Meeting of the Association for Computational Linguistics (ACL) Findings. 2021.
  • Qing Lyu, Hongming Zhang, Elior Sulem, and Dan Roth. Zero-shot Event Extraction via Transfer Learning: Challenges and Insights. Annual Meeting of the Association for Computational Linguistics (ACL). 2021. (Short Paper)
  • Haoyu Wang, Muhao Chen, Hongming Zhang, and Dan Roth. Joint Constrained Learning for Event-Event Relation Extraction. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. [PAPER] [CODE]

KG for NLP

  • Hongming Zhang, Yan Song, Yangqiu Song, and Dong Yu. Knowledge-aware Pronoun Coreference Resolution. Annual Meeting of the Association for Computational Linguistics (ACL). 2019. [PAPER] [CODE] [PPT]
  • Hongming Zhang, Yan Song, and Yangqiu Song. Incorporating Context and External Knowledge for Pronoun Coreference Resolution. North American Chapter of the Association for Computational Linguistics (NAACL-HLT). 2019. [PAPER] [CODE] [PPT]

2021

  • Haoyu Wang, Hongming Zhang, Muhao Chen and Dan Roth. Learning Constraints and Descriptive Segmentation for Subevent Detection. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021.
  • Yanai Elazar, Hongming Zhang, Yoav Goldberg and Dan Roth . Back to Square One: Bias Detection, Training and Commonsense Disentanglement in the Winograd Schema. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021.
  • Xintong Yu, Hongming Zhang, Yangqiu Song, Changshui Zhang, Kun Xu and Dong Yu . Exophoric Pronoun Resolution in Dialogues with Topic Regularization. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021.
  • Tianqing Fang, Weiqi Wang, Sehyun Choi, Shibo Hao, Hongming Zhang, Yangqiu Song and Bin He . Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2021.
  • Tianqing Fang, Haojie Pan, Hongming Zhang, Yangqiu Song, Kun Xu, Dong Yu. Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge. Conference on Automated Knowledge Base Construction (AKBC). 2021.
  • Hongming Zhang, Haoyu Wang, and Dan Roth. Zero-shot Label-Aware Event Trigger and Argument Classification. Annual Meeting of the Association for Computational Linguistics (ACL) Findings. 2021. [PAPER] [CODE & DATA]
  • Qing Lyu, Hongming Zhang, Elior Sulem, and Dan Roth. Zero-shot Event Extraction via Transfer Learning: Challenges and Insights. Annual Meeting of the Association for Computational Linguistics (ACL). 2021. (Short Paper) [PAPER] [CODE & DATA]
  • Xinran Zhao, Esin Durmus, Hongming Zhang, and Claire Cardie. Leveraging Topic Relatedness for Argument Persuasion. Annual Meeting of the Association for Computational Linguistics (ACL) Findings. 2021. (Short Paper)
  • Hongming Zhang, Yintong Huo, Xinran Zhao, Yangqiu Song, and Dan Roth. Learning Contextual Causality from Time-consecutive Images. Causality in Vision workshop at CVPR 2021. [PAPER] [CODE & DATA]
  • Tianqing Fang, Hongming Zhang, Weiqi Wang, Yangqiu Song, and Bin He. DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge. The Web Conference (WWW). 2021. [PAPER] [CODE & DATA]
  • Jiaxin Bai, Hongming Zhang, Yangqiu Song, and Kun Xu. Joint Coreference Resolution and Character Linking for Multiparty Conversation. The European Chapter of the Association for Computational Linguistics (EACL). 2021. [PAPER] [CODE & DATA]

2020

  • Muhao Chen, Hongming Zhang, Haoyu Wang, and Dan Roth. What Are You Trying to Do? Semantic Typing of Event Processes. The SIGNLL Conference on Computational Natural Language Learning (CoNLL). 2020. [PAPER] [CODE & DATA] (Best Paper Nomination)
  • Hongming Zhang, Muhao Chen, Haoyu Wang, Yangqiu Song, and Dan Roth. Analogous Process Structure Induction for Sub-event Sequence Prediction. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. [PAPER] [CODE & DATA] [PPT]
  • Haoyu Wang, Muhao Chen, Hongming Zhang, and Dan Roth. Joint Constrained Learning for Event-Event Relation Extraction. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. [PAPER] [CODE]
  • Changlong Yu, Jialong Han, Peifeng Wang, Yangqiu Song, Hongming Zhang, Wilfred Ng, and Shuming Shi. When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. [PAPER] [CODE]
  • Changlong Yu, Hongming Zhang, Yangqiu Song, Wilfred Ng, and Lifeng Shang. Enriching Large-Scale Eventuality Knowledge Graph with Entailment Relations. Conference on Automated Knowledge Base Construction (AKBC). 2020. [PAPER] [CODE & DATA] [PPT]
  • Hongming Zhang, Daniel Khashabi, Yangqiu Song, and Dan Roth. TransOMCS: From Linguistic Graphs to Commonsense Knowledge. International Joint Conference on Artificial Intelligence (IJCAI). 2020. [PAPER] [CODE & DATA] [PPT]
  • Hongming Zhang*, Xinran Zhao*, and Yangqiu Song. WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge. Annual Meeting of the Association for Computational Linguistics (ACL). 2020. [PAPER] [CODE & DATA] [PPT]
  • Hongming Zhang*, Xin Liu*, Haojie Pan*, Yangqiu Song, and Cane Wing-Ki Leung. ASER: A Large-scale Eventuality Knowledge Graph. The Web Conference (WWW). 2020. [PAPER] [CODE & DATA] [PPT]

2019

  • Hongming Zhang*, Jiaxin Bai*, Yan Song, Kun Xu, Changlong Yu, Yangqiu Song, Wilfred Ng, and Dong Yu. Multiplex Word Embeddings for Selectional Preference Acquisition. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2019. [PAPER] [CODE]
  • Xintong Yu*, Hongming Zhang*, Yangqiu Song, Yan Song, and Changshui Zhang. What You See is What You Get: Visual Pronoun Coreference Resolution in Conversations. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2019. [PAPER] [CODE]
  • Nedjma Ousidhoum, Zizheng Lin, Hongming Zhang, Yangqiu Song, and Dit-Yan Yeung. Multilingual and Multi-aspect Hate Speech Analysis. Conference on Empirical Methods in Natural Language Processing (EMNLP). 2019. [PAPER] [CODE]
  • Hongming Zhang, Hantian Ding, and Yangqiu Song. SP-10K: A Large-Scale Evaluation Set for Selectional Preference Acquisition. Annual Meeting of the Association for Computational Linguistics (ACL). 2019. [PAPER] [CODE & DATA]
  • Hongming Zhang, Yan Song, Yangqiu Song, and Dong Yu. Knowledge-aware Pronoun Coreference Resolution. Annual Meeting of the Association for Computational Linguistics (ACL). 2019. [PAPER] [CODE] [PPT]
  • Hongming Zhang, Yan Song, and Yangqiu Song. Incorporating Context and External Knowledge for Pronoun Coreference Resolution. North American Chapter of the Association for Computational Linguistics (NAACL-HLT). 2019. [PAPER] [CODE] [PPT]

2018

  • Hongming Zhang, Liwei Qiu, Lingling Yi, and Yangqiu Song. Scalable Multiplex Network Embedding. International Joint Conference on Artificial Intelligence (IJCAI). 2018. [PAPER] [CODE] [PPT]

Selected Awards

  • SENG Academic Award for Continuing PhD students, HKUST (Sep 2020)
  • Microsoft Research Asia Fellowship, Microsoft (Nov 2019)
  • Tencent Rhino-Bird Scholarship, Tencent (Oct 2019)
  • Hong Kong Ph.D. Fellowship, Hong Kong Government (2018-Present)
  • Rhino-Bird Program, Tencent (Oct 2018)
  • Excellent Research Award, HKUST (Sep 2018)
  • Academic Achievement Medal, HKUST (Jun 2016)
  • Dean’s List, HKUST (2012-2015)
  • Academic Excellence Award, HKUST (Apr 2014)

Academic Service

  • Journal Editorial Board: Semantic Web Journal special edition on Commonsense Knowledge and Reasoning; Frontiers in Big Data.
  • Journal Reviewer: Applied Network Science; Computer Science and Language; IEEE Transactions on Neural Networks and Learning Systems; NeuralComputing.
  • Senior PC: IJCAI'21.
  • PC: ACL'21; EMNLP'21; NAACL'21; IJCAI'22; AAAI'21-22; COLING'20; AACL'20; CIKM'19; AKBC'21; NLPCC'19,21.
  • Conference External Reviewer: ACL'18-19; AAAI'19; KDD'18; NIPS'18; ICDM'18; CIKM'18.
  • Others: IJCAI 2019 WebMaster.

Working Experience

Teaching Experience

  • COMP4331: Data Mining. (Fall 2019)
  • COMP4332/RMBI4310: Big Data Mining. (Spring 2019)
  • COMP1022Q: Introduction to Computing with Excel VBA (Fall/Spring 2018)