Relation/Entity-Centric Reading Comprehension
This work addresses the fundamental problem of language understanding in AI, which is crucial for developing more intelligent systems, but it appears incremental as it builds on existing reading comprehension frameworks.
The thesis tackles the challenge of machine understanding of human language by focusing on reading comprehension through question answering tasks that measure understanding of entities and their relationships, as these are key to representing natural language semantics.
Constructing a machine that understands human language is one of the most elusive and long-standing challenges in artificial intelligence. This thesis addresses this challenge through studies of reading comprehension with a focus on understanding entities and their relationships. More specifically, we focus on question answering tasks designed to measure reading comprehension. We focus on entities and relations because they are typically used to represent the semantics of natural language.