.png){kind=icon}
返回
Finding decision jumps in text classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2019.08.082.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Text classification is one of the key problems in natural language processing (NLP), and in early years, it was usually accomplished by feature-based machine learning models. Recently, the deep neural network has become a powerful learning machine, making it possible to work with text itself as raw input for the classification problems. However, existing neural networks are typically end-to-end and lack explicit interpretation of the prediction. In this paper, we propose JUMPER, a novel framework that models text classification as a sequential decision process. Generally, JUMPER is a neural system that scans a piece of text sequentially and makes classification decisions at the time it wishes, which is inspired by the cognitive process of human text reading. In our framework, both the classification result and when to make the classification are part of the decision process, controlled by a policy network and trained with reinforcement learning. Experimental results of real-world applications demonstrate the following properties of a properly trained JUMPER: (1) it tends to make decisions whenever the evidence is enough, therefore reducing total text reading by 30-40% and often finding the key rationale of the prediction; and (2) it achieves classification accuracy better than or comparable to state-of-the-art models in several benchmark and industrial datasets. We further conduct a simulation experiment with mock data, which confirms that JUMPER is able to make a decision at the theoretically optimal decision position. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Text classification
Reinforcement learning
Weak supervision
Rationalizing neural prediction
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
分享收藏Towards understanding of electrolyte degradation in lithium-mediated non-aqueous electrochemical ammonia synthesis with gas chromatography-mass spectrometry.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAI分享收藏 没有更多内容
没有更多内容