IC Colloquium: Neuro-symbolic Representations for Commonsense Knowledge and Reasoning
Event details
| Date | 02.03.2020 |
| Hour | 10:15 › 11:15 |
| Location | |
| Category | Conferences - Seminars |
By: Antoine Bosselut - University of Washington
IC Faculty candidate
Abstract:
Situations described using natural language are richer than what humans explicitly communicate. For example, the sentence "She pumped her fist" connotes many potential auspicious causes. For machines to understand natural language, they must be able to reason about the commonsense inferences that underlie explicitly stated information. In this talk, I will present work on combining traditional symbolic knowledge and reasoning techniques with modern neural representations to endow machines with these capacities.
First, I will describe COMET, an approach for learning commonsense knowledge about unlimited situations and concepts using transfer learning from language to knowledge. Second, I will demonstrate how these neural knowledge representations can dynamically construct symbolic graphs of contextual commonsense knowledge, and how these graphs can be used for interpretable, generalized reasoning. Finally, I will discuss future research directions on conceptualizing NLP as commonsense simulation, and the impact of this framing on difficult open-ended tasks such as story generation and dialogue.
Bio:
Antoine Bosselut is a PhD Student at the University of Washington advised by Professor Yejin Choi, and a student researcher at the Allen Institute for Artificial Intelligence. His research focuses on building systems for commonsense knowledge representation and reasoning that combine the strengths of modern neural and traditional symbolic methods. He was previously a student researcher on the Deep Learning team at Microsoft Research from 2017 to 2018.
More information
IC Faculty candidate
Abstract:
Situations described using natural language are richer than what humans explicitly communicate. For example, the sentence "She pumped her fist" connotes many potential auspicious causes. For machines to understand natural language, they must be able to reason about the commonsense inferences that underlie explicitly stated information. In this talk, I will present work on combining traditional symbolic knowledge and reasoning techniques with modern neural representations to endow machines with these capacities.
First, I will describe COMET, an approach for learning commonsense knowledge about unlimited situations and concepts using transfer learning from language to knowledge. Second, I will demonstrate how these neural knowledge representations can dynamically construct symbolic graphs of contextual commonsense knowledge, and how these graphs can be used for interpretable, generalized reasoning. Finally, I will discuss future research directions on conceptualizing NLP as commonsense simulation, and the impact of this framing on difficult open-ended tasks such as story generation and dialogue.
Bio:
Antoine Bosselut is a PhD Student at the University of Washington advised by Professor Yejin Choi, and a student researcher at the Allen Institute for Artificial Intelligence. His research focuses on building systems for commonsense knowledge representation and reasoning that combine the strengths of modern neural and traditional symbolic methods. He was previously a student researcher on the Deep Learning team at Microsoft Research from 2017 to 2018.
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host: Martin Jaggi