ReasoNet: Learning to Stop Reading in Machine Comprehension

Yelong Shen, Po-Sen Huang, Jianfeng Gao, Weizhu Chen

Invalid Date (modified: Nov 04, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: Teaching a computer to read a document and answer general questions pertaining to the document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architecture called Reasoning Network ({ReasoNet}) for machine comprehension tasks. ReasoNet makes 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, ReasoNet introduces a termination state to relax this constraint on the reasoning depth. With the use of reinforcement learning, ReasoNet 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. ReasoNet has achieved state-of-the-art performance in machine comprehension datasets, including unstructured CNN and Daily Mail datasets, and a structured Graph Reachability dataset.
  • TL;DR: ReasoNet Reader for machine reading and comprehension
  • Conflicts:
  • Keywords: Deep learning, Natural language processing
0 Replies