CIS - "Get to know your neighbors" Seminar series - Prof. Antoine Bosselut

Thumbnail

Event details

Date 28.03.2022 15:1516:15  
Speaker Prof. Antoine Bosselut
Location Online
Category Conferences - Seminars
Event Language English
Title: Neuro-symbolic Scaffolds for Commonsense Representation and Reasoning

Abstract: 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.

Bio: 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.


The Center for Intelligent Systems at EPFL (CIS) is a collaboration among IC, ENAC, SB; SV and STI that brings together researchers working on different aspects of Intelligent Systems.
In order to promote exchanges among researchers and encourage the creation of new, collaborative projects, CIS is organizing a "Get to know your neighbors" series. Each seminar will consist of one short overview presentation geared to the general public at EPFL.   
 
The CIS seminar will take place In hybrid mode: Room INF 328 and by Zoom:  https://epfl.zoom.us/j/64002897669

Please connect to your zoom account using your "@epfl.ch" address, as this live event is only open to the EPFL community
Monday, March 28th, 2022 from 3:15 to 4:15 pm
NB: Video recordings of the seminars will be made available on our website and published on our social media pages

Practical information

  • General public
  • Free

Organizer

  • CIS

Contact

Tags

CISSBSTIICENACApprentissage automatique Intelligence artificielle Robotique Vision par ordinateur Artificial intelligence AI Robotics Computer vision

Share