ReasoNet: Learning to Stop Reading in Machine Comprehension
Yelong Shen, Po-Sen Huang, Jianfeng Gao, Weizhu Chen Microsoft ResearchOne Microsoft WayRedmondWA98053 yeshen, pshuang, jfgao,
Abstract
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 achieve superior performance in machine comprehension datasets, including unstructured CNN and Daily Mail datasets, the Stanford SQuAD dataset, and a structured Graph Reachability dataset.
中文速览
机器阅读理解要求计算机读懂文章并回答问题，而现有多轮推理模型总是固定推理轮数，无法根据问题难易灵活调整。本文提出了一种叫做推理网络（Reasoning Network，ReasoNet）的新型神经网络，它引入了一个"终止门"机制，让模型在每一轮阅读后自主判断当前信息是否足够，从而动态决定继续阅读还是直接给出答案。由于终止决策是离散的，无法直接用反向传播训练，作者采用强化学习并设计了一种基于实例的自适应奖励基线来解决训练难题。在CNN/Daily Mail、Stanford SQuAD以及图可达性等多个数据集上，ReasoNet均取得了当时领先的成绩，证明让模型像人一样"读到懂为止"是提升阅读理解性能的有效思路。
原文 arXiv:1609.05284;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1609.05284v3