Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal

no code implementations • 23 May 2019 • Alex Long, Joel Mason, Alan Blair, Wei Wang

To address MH-QA specifically, we propose a Deep Reinforcement Learning based method capable of learning sequential reasoning across large collections of documents so as to pass a query-aware, fixed-size context subset to existing models for answer extraction.

Decision Making Multi-Hop Reading Comprehension +4