ReasoNet: Learning to Stop Reading in Machine Comprehension
This addresses the challenge of teaching computers to read and answer questions from documents, with incremental improvements in reasoning depth control.
The paper tackles the problem of machine comprehension by introducing ReasoNet, a neural network that dynamically determines when to stop reading using reinforcement learning, achieving exceptional performance on multiple datasets including CNN/Daily Mail, SQuAD, and Graph Reachability.
Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architecture called the Reasoning Network (ReasoNet) for machine comprehension tasks. ReasoNets make use of multiple turns to effectively exploit and then reason over the relation among queries, documents, and answers. Different from previous approaches using a fixed number of turns during inference, ReasoNets introduce a termination state to relax this constraint on the reasoning depth. With the use of reinforcement learning, ReasoNets can dynamically determine whether to continue the comprehension process after digesting intermediate results, or to terminate reading when it concludes that existing information is adequate to produce an answer. ReasoNets have achieved exceptional performance in machine comprehension datasets, including unstructured CNN and Daily Mail datasets, the Stanford SQuAD dataset, and a structured Graph Reachability dataset.