# ReasoNet: Learning to Stop Reading in Machine Comprehension

arXiv: https://arxiv.org/abs/1609.05284 · HTML: https://mlsanity.com/paper/1609.05284/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2016.

## Built on by (most cited first, 21 of 21)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail](https://mlsanity.com/paper/2110.08300/) (2021)
- [A Survey on Dynamic Neural Networks for Natural Language Processing](https://mlsanity.com/paper/2202.07101/) (2022)
- [Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation](https://mlsanity.com/paper/2201.05088/) (2022)
- [Asking questions on handwritten document collections](https://mlsanity.com/paper/2110.00711/) (2021)
- [E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models](https://mlsanity.com/paper/2203.00748/) (2022)
- [FinBERT-MRC: financial named entity recognition using BERT under the machine reading comprehension paradigm](https://mlsanity.com/paper/2205.15485/) (2022)
- [Boosted Dynamic Neural Networks](https://mlsanity.com/paper/2211.16726/) (2022)
- [DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models](https://mlsanity.com/paper/2311.08623/) (2023)
- [Improving Question Answering Performance Using Knowledge Distillation and Active Learning](https://mlsanity.com/paper/2109.12662/) (2021)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics](https://mlsanity.com/paper/2212.04070/) (2022)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches](https://mlsanity.com/paper/2212.04072/) (2022)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension](https://mlsanity.com/paper/2107.07957/) (2021)
- [An Automated Question-Answering Framework Based on Evolution Algorithm](https://mlsanity.com/paper/2201.10797/) (2022)
- [Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Experts](https://mlsanity.com/paper/2210.01750/) (2022)
- [KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information](https://mlsanity.com/paper/2301.07341/) (2023)
- [A novel interface for adversarial trivia question-writing](https://mlsanity.com/paper/2404.00011/) (2024)
- [Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization](https://mlsanity.com/paper/2407.14000/) (2024)
- [Learning to Construct Knowledge through Sparse Reference Selection with Reinforcement Learning](https://mlsanity.com/paper/2509.05874/) (2025)

## Abstract (arXiv)

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.