.png){kind=icon}
返回
Learning to activate logic rules for textual reasoning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2018.06.012.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most current textual reasoning models cannot learn human-like reasoning process, and thus lack interpretability and logical accuracy. To help address this issue, we propose a novel reasoning model which learns to activate logic rules explicitly via deep reinforcement learning. It takes the form of Memory Networks but features a special memory that stores relational tuples, mimicking the Image Schema'' in human cognitive activities. We redefine textual reasoning as a sequential decision-making process modifying or retrieving from the memory, where logic rules serve as state-transition functions. Activating logic rules for reasoning involves two problems: variable binding and relation activating, and this is a first step to solve them jointly. Our model achieves an average error rate of 0.7% on bAbI-20, a widely-used synthetic reasoning benchmark, using less than 1k training samples and no supporting facts. (C) 2018 Elsevier Ltd. All rights reserved.
Keyword:
Natural language reasoning
Memory networks
Image schema
Logic rules
Reinforcement learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Seasonal Variation in Physicochemical Parameters and Heavy Metals in Water of Upper Lake of Bhopal
PREAI
分享收藏Hybrid computing using a neural network with dynamic external memory使用具有动态外部存储器的神经网络进行混合计算.png)
NATURE
NATUREIF48.5
PREAI
分享收藏