Dr. Jae Hee Lee

About Me

I am a postdoctoral research associate in the Knowledge Technology Group, University of Hamburg.

My research aims to develop deep learning models for grounded language understanding by leveraging multimodal information. My particular focus is in on spatial language understanding and compositional language grounding.

Education

• Dr. rer. nat. in Computer Science, University of Bremen, Germany (2013)
• Diplom in Mathematics, University of Bremen, Germany (2009)

Research Interests

• Artificial Intelligence
• Multimodal Learning
• Grounded Language Understanding
• Spatial Reasoning

Research Experience

• University of Hamburg, Hamburg, Germany (2020–present)
  • Project: Neurocognitive Models of Crossmodal Language Learning
  • Topics: grounded language understanding, multimodal learning, representation learning
• Cardiff University, Cardiff, UK (2018–2020)
  • Project: Formal Lexically Informed Logics for Searching the Web
  • Topics: knowledge graph embeddings, natural language processing
• University of Technology Sydney, Sydney, Australia (2016–2017)
  • Feodor Lynen Research Fellowship
  • Topics: temporal reasoning, multi-agent systems
• The Australian National University, Canberra, Australia (2015)
  • Project: Artificial Intelligence Meets Wireless Sensor Networks
  • Topics: spatial reasoning, physical reasoning
• University of Bremen, Bremen, Germany (2009–2014)
  • Project: Reasoning about Paths, Shapes, and Configuration
  • Topics: spatial reasoning, knowledge representation

Research Grants and Awards

• Bremen-Cardiff Alliance Collaborative Fund, Cardiff University, UK (2019)
• UTS Blue Sky Research Scheme, University of Technology Sydney, Sydney (2017)
• Feodor Lynen Research Fellowship, Alexander von Humboldt Foundation, Germany (2016–2017)
• Fachbereichspreis Mathematik (diploma thesis award), University of Bremen (2009)
• DAAD-KOSEF Scholarship, DAAD, Germany (2008)
• Third Prize at the Regional Contest Jugend Forscht Bremen (2001)
• Senator-Friedrich-Cordewener-Prize (Special Prize) at the Regional Contest Jugend Forscht Bremen (2001)

Recent Publications

• Mengdi Li, Cornelius Weber, Matthias Kerzel, Jae Hee Lee, Zheni Zeng, Zhiyuan Liu, Stefan Wermter. Robotic Occlusion Reasoning for Efficient Object Existence Prediction, IROS 2021 (to appear).

• A. Eisermann, J. H. Lee, C. Weber, S. Wermter. Generalization in Multimodal Language Learning from Simulation, IJCNN 2021.

• J.H. Lee, J. Camacho-Collados, L. Espinosa Anke, S. Schockaert, Capturing Word Order in Averaging Based Sentence Embeddings, ECAI 2020.

• S. Kong, J. Bai, J.H. Lee, D. Chen, A. Allyn, M. Stuart, M. Pinsky, K. Mills, C.P. Gomes. Deep Hurdle Networks for Zero-Inflated Multi-Target Regression: Application to Multiple Species Abundance Estimation, IJCAI 2020.

  Full publication list available on DBLP

Teaching

• Supervisor, Neural Networks Seminar, University of Hamburg (2020, 2021)
• Supervisor, Bio-inspired Artificial Intelligence Seminar, University of Hamburg (2020, 2021)
• Teaching Assistant, Mathematics III, University of Bremen (2008)
• Teaching Assistant, Linear Algebra II, University of Bremen (2007)
• Organizer, Linear Algebra I + II Seminar, University of Bremen (2007)
• Teaching Assistant, Linear Algebra I, University of Bremen (2006)

Thesis Supervision

• Learning Bidirectional Translation Between Robot Actions and Linguistic Descriptions, Markus Heidrich, BSc (2021)
• Using the Reformer for Efficient Summarization, Yannick Wehr, BSc (2020)
• Generalization in Multi-Modal Language Learning from Simulation, Aaron Eisermann, BSc (2020)
• Commonsense Validation and Explanation, Christian Rahe, BSc (2020)

News

• Senior program committee member, AAAI 2022
• Program committee member, IJCAI-ECAI 2022

Personal Homepage

• jaeheelee.de