Machine Reasoning
Research
We innovate neural networks reaching symbolic-level logical reasoning and inheriting features of traditional networks, to guarantee the explainability and the reliability in real applications, while preserving their power of prediction.
Teaching
- From Machine Learning to Machine Reasoning (part of the Foundation AI series)
Professional Activities
- Contact chair. Neural Reasoning and Mathematical Discovery – An Interdisciplinary Two-Way Street. NeurMAD@AAAI'25 Workshop
- Co-organiser. The 1st Workshop on Computational Humor (CHum) @ Coling 2025
- Lead-organiser. Bridging Neurons and Symbols for Natural Language Processing and Knowledge Graphs Reasoning @ LREC-Coling 2024.
- Lead-organiser. Dagstuhl Seminar "Structure and Learning", 2021.
Publications
- Tiansi Dong, Mateja Jamnik, Pietro Liò (2025). Neural Reasoning for Sure Through Constructing Explainable Models. AAAI.
- Tiansi Dong, Writwick Das, Rafet Sifa (2025). Bridging Language and Scenes through Explicit 3-D Model Construction. NeusymBridge@COLING.
- Tiansi Dong, et. al., (2024). Word Sense Disambiguation as a Game of Neurosymbolic Darts. NeusyBridge@LREC-COLING.
- Tiansi Dong (2021). A Geometric Approach to the Unification of Symbolic Structures and Neural Networks. Springer-Nature.
- Tiansi Dong, et. al. (2019). Triple Classification Using Regions and Fine-Grained Entity Typing. AAAI.
- Tiansi Dong, et. al. (2019). Imposing Category Trees Onto Word-Embeddings Using A Geometric Construction, ICLR.
- Tiansi Dong, et. al., (2012). Recognizing Variable Environment -- The Theory of Cognitive Prism, Spinger.
- Tiansi Dong (2008). A Comment on RCC: from RCC to RCC++, Journal of Philosophical Logic 37(4): 319-352.