Xin Liu 劉昕

fifth-year Ph.D. Student

Knowledge Computation Group

Department of Computer Science and Engineering

The Hong Kong University of Science and Technology

Clearwater Bay, Kowloon, Hong Kong

E-mail: xliucr [AT] cse [dot] ust [dot] hk

My Google Scholar, GitHub, Linkedin, and Curriculum Vitae (Oct. 2022)


My Photo

Biography

I am a final-year Ph.D. candidate at Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, supervised by Prof. Yangqiu Song. Before that, I received my B.E. degree at School of Data and Computer Science, Sun Yat-sen University in June 2018, supervised by Prof. Rong Pan.

Research Interests

  • Natural Language Understanding
  • Graph Reasoning

Topics in progress
  • Language Model Prompt and Probing for Linguistic Knowledge
  • Neural Symbolic Reasoning
  • Knowledge-Aware Natural Language Processing
Previous topics:
  • Commonsense Knowledge Graph Construction
  • OpenIE
  • Hierarchical Text Classification
  • Word Representation Learning in Social Networks
  • Open-domain Question Answering
  • Graph Database

Publications  

* means equal contribution.

Journal Articles

  1. Hongming Zhang*, Xin Liu*, Haojie Pan*, Haowen Ke, Jiefu Ou, Tianqing Fang, and Yangqiu Song. ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities.
    Artificial Intelligence, 2022. [pdf] [code] [homepage]

Conference Publications

  1. Huiru Xiao, Xin Liu, Yangqiu Song, Ginny Y. Wong, Simon See. Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform.
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022. [pdf] [code]
  2. Xin Liu, Jiayang Cheng, Yangqiu Song, Xin Jiang. Boosting Graph Structure Learning with Dummy Nodes.
    In Proceedings of the International Conference on Machine Learning (ICML), 2022. [pdf] [code] [slides]
  3. Xin Liu, Yangqiu Song. Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching.
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2022. [pdf] [code] [slides]
  4. Xin Liu, Jiefu Ou, Yangqiu Song, Xin Jiang. Exploring Discourse Structures for Argument Impact Classification.
    In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2021. [pdf] [code] [slides]
  5. Xin Liu, Jiefu Ou, Yangqiu Song, Xin Jiang. On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification.
    In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2020. [pdf] [code] [slides]
  6. Xin Liu, Haojie Pan, Mutian He, Yangqiu Song, Xin Jiang, Lifeng Shang. Neural Subgraph Isomorphism Counting.
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020. [pdf] [code] [slides]
  7. Hongming Zhang*, Xin Liu*, Haojie Pan*, Yangqiu Song, Cane Wing-Ki Leung. ASER: A Large-scale Eventuality Knowledge Graph.
    In World Wide Web Conference (WWW), 2020. [pdf] [code] [slides]
  8. Jie Huang, Xin Liu, and Yangqiu Song. Hyper-Path-Based Representation Learning for Hyper-Networks.
    In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM), 2019. [pdf] [code] [slides]
  9. Yan Liang, Xin Liu, Jianwen Zhang, and Yangqiu Song. Relation Discovery with Out-of-Relation Knowledge Base as Supervision.
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL-HLT), 2019. [pdf] [code]
  10. Ziqian Zeng, Wenxuan Zhou, Xin Liu, and Yangqiu Song. A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification.
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL-HLT), 2019. [pdf] [code]
  11. Huiru Xiao, Xin Liu, and Yangqiu Song. Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification.
    In World Wide Web Conference (WWW), 2019 (Short Paper). [pdf] [code]
  12. Ziqian Zeng*, Xin Liu*, and Yangqiu Song. Biased RandomWalk based Social Regularization for Word Embeddings.
    In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2018. [pdf] [code] [slides]

Awards

  • HKUST RedBird Academic Excellence Award for Continuing PhD Students (HKUST, 2022)
  • HKUST CSE Professor Samuel Chanson Best Teaching Assistant Award (HKUST, 2020)
  • HKUST SENG Academic Award for Continuing PhD Students (HKUST, 2020)
  • Outstanding Graduate (SYSU, 2018)
  • Outstanding Graduate Thesis (SYSU, 2018)
  • The First Prize, Guangdong Collegiate Programming Contest (Computer Academic of Guangdong, 2018)
  • Top 10, Tencent Social Advertising College Algorithm Competition (Tencent, 2017 and 2018)
  • Meritorious Winner, Mathematical Contest in Modeling/Interdisciplinary Contest in Modeling (COMAP, 2017)
  • National Scholarships (SYSU, 2015, 2016 and 2017)

Working Experience

  • Knowledge Computation Group, the Hong Kong University of Science and Technology (Jan. 2018 - July 2018)
  • Cloud & Mobile Group, Microsoft Research Asia (June 2017 - Dec. 2017)

Academic Service

  • Program Committee Member: CIKM'19,21   AAAI'21,22   IJCAI'21,22   NAACL-HLT'22   ICML'22   SIGKDD'22
  • Conference Reviewer: ACL'19   EMNLP'19   IJCAI'19,20   SIGKDD'19,20,21
  • Volunteer: Baidu World Conference'16   IJCAI'18,19,20   NAACL-HLT'19   KDD'20

Teaching Experience

  • MSBD5018H: Natural Language Processing. (Spring 2022)
  • MSBD6000H: Natural Language Processing. (Spring 2021)
  • COMP4332/RMBI4310: Big Data Mining. (Spring 2020)
  • COMP4332/RMBI4310: Big Data Mining. (Spring 2019)
  • COMP4901K/MATH4824B: Machine Learning for Natural Language Processing. (Fall 2018)