Hanlei Zhang

Hanlei Zhang

Intent Analysis, Natural Language Processing, and Multimodal Machine Learning.

About me

I am currently in my fifth year as a Ph.D. student in the THUIAR group with State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology (DCST), Tsinghua University, Beijing, China. Under the guidance of Prof. Hua Xu, my research primarily focuses on open set recognition, clustering, multimodal machine learning, and natural language processing.

My work centers around analyzing human intentions in open-world and multimodal scenarios, leading to the development of significant tasks including open intent detection, new intent discovery, and multimodal intent analysis. In pursuit of advancing research in these domains, we have contributed a range of foundational and pioneering works. This includes the development of algorithms such as ADB, DA-ADB, DeepAligned, and USNID, as well as the creation of datasets like MIntRec and MIntRec2.0, and toolkits such as TEXTOIR. As the first author, I have published 8 papers in prestigious AI journals and conferences (e.g., ICLR, IEEE TKDE, ACL, AAAI, ACM MM, IEEE/ACM TASLP), and these works have been cited by over 410 times (Google Scholar Citations).

  • Multimodal Intent Recognition Datasets (MIntRec, MIntRec2.0)
  • Text Open Intent Recognition Platform (Toolkit)
  • Open Knowledge Discovery Reading List (Link)

Education

  • Sep. 2020 - now. Ph.D. candidate, Department of Computer Science and Technology, Tsinghua University, China.
  • Sep. 2016 - Jun. 2020. B.S., Department of Computer Science and Technology, Beijing Jiaotong University, China.

Experience

  • Aug. 2024 - now. Research Internship, Wechat AI, Pattern Recognition Center, Tencent, Beijing, China.
  • Dec. 2018 - Jun. 2019. Visiting student in THUMT, advised by Prof. Yang Liu, Tsinghua University, China.

News

  • [Aug. 2024] Our paper “Discovering New Intents with Deep Aligned Clustering” has reached its 100th citation!
  • [Jul. 2024] Our paper “Deep Open Intent Classification with Adaptive Decision Boundary” has reached its 100th citation!
  • [May. 2024] Got one first-author full paper accepted by ACL 2024. See you in Bangkok, Thailand!
  • [Jan. 2024] Got one first-author full paper accepted by ICLR 2024. See you in Vienna, Austria!
  • [Dec. 2023] Got one full paper accepted by AAAI 2024. Congratulations to Qianrui!
  • [Dec. 2023] Got one first-author full paper accepted by IEEE TKDE.
  • [Mar. 2023] Got one first-author full paper accepted by IEEE/ACM TASLP.
  • [Sep. 2022] Released MIntRec, a novel benchmark dataset for multimodal intent recognition, available for public use resources, enjoy it!
  • [Jun. 2022] Got one first-author full paper accepted at ACM MM 2022.
  • [Aug. 2021] Released the first text open intent recognition toolkit (TEXTOIR), integrating a series of methods in open intent detection and discovery, enjoy it!
  • [May. 2021] Got one first-author demo paper accepted at ACL 2021.
  • [Jan. 2021] Released the first open knowledge discovery reading list, enjoy it!
  • [Dec. 2020] Got two first-author full papers accepted at AAAI 2021.
  • [Nov. 2019] Got one full paper accepted at AAAI 2020.

Publications

  • Hanlei Zhang, Hua Xu, Fei Long, Xin Wang, Kai Gao. Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances. 2024. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. (ACL 2024 Main, CCF-A) [paper] [code] [bibtex]
  • Hanlei Zhang*, Xin Wang*, Hua Xu, Qianrui Zhou, Kai Gao, Jianhua Su, Jinyue Zhao, Wenrui Li, Yanting Chen. MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations. 2024. Proceedings of the 12th International Conference on Learning Representations. (ICLR 2024, TH-CPL-A) [paper] [code] [bibtex]
  • Hanlei Zhang, Hua Xu, Xin Wang, Fei Long, Kai Gao. A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery. 2023. IEEE Transactions on Knowledge and Data Engineering. (IEEE TKDE, CCF-A) [paper] [code] [bibtex]
  • Hanlei Zhang, Hua Xu, Shaojie Zhao, Qianrui Zhou. Learning Discriminative Representations and Decision Boundaries for Open Intent Detection. 2023. IEEE/ACM Transactions on Audio, Speech, and Language Processing Volume 31. (IEEE/ACM TASLP, TH-CPL-A) [paper] [code] [bibtex]
  • Hanlei Zhang, Hua Xu, Xin Wang, Qianrui Zhou, Shaojie Zhao, Jiayan Teng. MIntRec: A New Dataset for Multimodal Intent Recognition. 2022. Proceedings of the 30th ACM International Conference on Multimedia. (ACM MM 2022, CCF-A) [paper] [code] [bibtex]
  • Hanlei Zhang*, Xiaoteng Li*, Hua Xu*, Panpan Zhang, Kang Zhao, Kai Gao. TEXTOIR: An Integrated and Visualized Platform for Open Intent Recognition. 2021. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations. (ACL-IJCNLP 2021 Demo, CCF-A) [paper] [toolkit] [demo] [bibtex]
  • Hanlei Zhang, Hua Xu, Ting-En Lin. Deep Open Intent Classification with Adaptive Decision Boundary. 2021. Proceedings of the 35th AAAI Conference on Artificial Intelligence. (AAAI 2021, CCF-A) [paper][code][bibtex]
  • Hanlei Zhang, Hua Xu, Ting-En Lin, Rui Lyu. Discovering New Intents with Deep Aligned Clustering. 2021. Proceedings of the 35th AAAI Conference on Artificial Intelligence. (AAAI 2021, CCF-A) [paper][code] [bibtex]
  • Qianrui Zhou, Hua Xu, Hao Li, Hanlei Zhang, Xiaohan Zhang, Yifan Wang, Kai Gao. Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition. 2024. Proceedings of the 37th AAAI Conference on Artificial Intelligence. (AAAI 2024, CCF-A) [paper][code] [bibtex]
  • Ting-En Lin, Hua Xu, Hanlei Zhang. Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement. 2020. Proceedings of the 34th AAAI Conference on Artificial Intelligence. (AAAI 2020, CCF-A) [paper][code][bibtex][slide]

(* indicates equal contribution)

Honor and Awards

Ph.D.

  • [Oct. 2024] National Scholarship for PhD Student. (Top 1%)
  • [Oct. 2023] Overall Excellence Scholarship (First Prize), Tsinghua University. (Top 5%)
  • [Dec. 2022] Apple Scholars in AI/ML Nomination.
  • [Oct. 2022] Overall Excellence Scholarship (First Prize), Tsinghua University. (Top 5%)
  • [Sep. 2022] Longfor Scholarship, DCST, Tsinghua University.
  • [Oct. 2021] Overall Excellence Scholarship (First Prize), Tsinghua University. (Top 5%)

Bachelor

  • [Jun. 2020] Beijing Outstanding graduates, from Beijing Jiaotong University.
  • [Apr. 2019] Meritorious Winner, MCM/ICM 2019.
  • [Nov. 2018] National Scholarship for Undergraduate Student (2018 No.01051). (Top 2%)
  • [Nov. 2018] Bronze Medal, International Collegiate Programming Contest (ACM-ICPC) Asia Regional Beijing Site 2018.
  • [Nov. 2017] National Scholarship for Undergraduate Student (2017 No.01086). (Top 2%)
  • [Nov. 2017] First prize, the Chinese Mathematics Competitions for College Students. (Top 5%)

Invited Talks

  • [Sep. 2022] MIntRec: A Novel Multimodal Intent Recognition Dataset. Talk at MLNLP. [video]
  • [Mar. 2021] Open intent detection and discovery in dialogue systems. Talk at AI TIME. [video]

Professional Services

Reviewer / Program Committee Member:

  • ICLR (2025)
  • NeurIPS (2023, 2024)
  • ACL (2023, 2024)
  • KDD (2023)
  • AAAI (2021)
  • IJCAI (2023, 2024)