Reasoning and Learning in Interactive Natural Language Systems

Suhr, Alane

Reasoning and Learning in Interactive Natural Language Systems

Abstract

Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities.

Description

264 pages

Date Issued

2022-12

Keywords

computer vision; language grounding; machine learning; natural language processing

Committee Chair

Artzi, Yoav

Committee Member

Naaman, Mor
Snavely, Keith

Degree Discipline

Computer Science

Degree Name

Ph. D., Computer Science

Degree Level

Doctor of Philosophy

Rights

Attribution-ShareAlike 4.0 International

Rights URI

https://creativecommons.org/licenses/by-sa/4.0/

Types

dissertation or thesis