22 July 2022
11 to 12 pm CET
Virtual
Exploring Qualitative Representations in Natural Language Semantics
Kenneth D. Forbus is the Walter P. Murphy Professor of Computer Science and Professor of Education at Northwestern University. His research interests include qualitative reasoning, analogical reasoning and learning, spatial reasoning, sketch understanding, natural language understanding, cognitive architecture, reasoning system design, intelligent educational software, and the use of AI in interactive entertainment. He is a Fellow of the Association for the Advancement of Artificial Intelligence, the Cognitive Science Society, the Association for Computing Machinery, and the American Association for the Advancement of Science. He is the inaugural recipient of the Herbert A. Simon Prize, a recipient of the Humboldt Research Award and served as Chair of the Cognitive Science Society.
People use qualitative representations to reason and learn about the continuous world. This suggests that qualitative representations have a role to play in natural language semantics. This talk will summarize my group's work in this area, including how QP theory constructs manifest in English, type-level versus instance-level qualitative models, analogical Q/A training, and work in progress to scale to handle a broader range of language.
Relevant papers:
McFate, C.J., Forbus, K. and Hinrichs, T. (2014). Using Narrative Function to Extract Qualitative Information from Natural Language Texts. Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, Québec City, Québec, Canada.
McFate, C., and Forbus, K. (2016). An Analysis of Frame Semantics of Continuous Processes. Proceedings of the 38th Annual Meeting of the Cognitive Science Society, Philadelphia, PA, August
Forbus, K. & Hinrichs, T. (2020). Unifying Instance-Level and Type-Level QP Frames for Natural Language Understanding, Proceedings of the 33rd International Workshop on Qualitative Reasoning
Ribeiro, D. & Forbus, K. (2021). Combining Analogy with Language Models for Knowledge Extraction, Proceedings of the Third Conference on Automatic Knowledge Base Construction.