Neuro-symbolic Scaffolds for Commonsense Representation and Reasoning
Prof. Antoine Bosselut, Head of the Natural Language Processing Lab NLP, EPFL
Monday, March 28, 2022 | 3:15 – 4:15pm | Hybrid INF 328
Or on-site INF 328
Natural language underspecifies the information-rich situations that it describes and communicates. For example, the sentence “She pumped her fist” connotes many potential auspicious causes. For machines to understand natural language, they must be able to make commonsense inferences that enrich explicitly stated information. However, current NLP systems lack the ability to ground the situations they read and write about to relevant world knowledge.
Moreover, they struggle to reason over available facts to generalize to future unseen events. In this talk, I will describe efforts at transforming modern language models into commonsense knowledge models by leveraging implicitly encoded knowledge representations. Then, I will discuss work in designing natural language reasoning systems that use knowledge graphs as a structural scaffold for aggregating information across relevant commonsense inferences.
Antoine Bosselut is an assistant professor in the School of Computer and Communication Sciences at the École Polytechnique Fédéral de Lausanne (EPFL) and the head of the Natural Language Processing (NLP) lab. Previously, he was a postdoctoral fellow at Stanford University and a Young Investigator at the Allen Institute for AI (AI2). He received his PhD at the University of Washington. He was named as a Forbes 30 under 30 for Science and Healthcare in Europe (2021). His research focuses on building knowledge-aware NLP systems, specializing in commonsense representation and reasoning.