Papers › ReasoNet: Learning to Stop Reading in Machine Comprehension

ReasoNet: Learning to Stop Reading in Machine Comprehension

17 Sep 2016arXiv:1609.05284archive 2025-07-28

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

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringReading ComprehensionReinforcement Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering CNN / Daily Mail ReasoNet CNN 74.7 #7 of 16 Archive leaderboard report
Question Answering CNN / Daily Mail ReasoNet Daily Mail 76.6 #7 of 16 Archive leaderboard report
Question Answering SQuAD1.1 ReasoNet (ensemble) EM 75.034 #123 of 213 Archive leaderboard report
Question Answering SQuAD1.1 ReasoNet (ensemble) F1 82.552 #123 of 213 Archive leaderboard report
Question Answering SQuAD1.1 ReasoNet (single model) EM 70.555 #161 of 213 Archive leaderboard report
Question Answering SQuAD1.1 ReasoNet (single model) F1 79.364 #161 of 213 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections