基于本体的可解释机器学习文本数据(CS.LG)---蔡小雪7100294

在本文中，我们介绍了一种新颖的解释框架，该框架基于基于本体的采样技术来学习可解释模型，以解释不可知预测模型。与现有方法不同，我们的算法考虑领域知识本体中描述的单词之间的上下文相关性，以生成语义解释。为了缩小解释的搜索空间（这是长而复杂的文本数据的主要问题），我们设计了一种可学习的锚算法，以更好地在本地提取解释。进一步引入了一套规则，涉及将学习到的可解释表示与锚点相结合以生成可理解的语义解释。在两个真实世界的数据集上进行的广泛实验表明，与基线方法相比，我们的方法产生了更精确和有见地的解释。

原文标题：Ontology-based Interpretable Machine Learning for Textual Data

原文：In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is a major problem of long and complicated text data, we design a learnable anchor algorithm, to better extract explanations locally. A set of regulations is further introduced, regarding combining learned interpretable representations with anchors to generate comprehensible semantic explanations. An extensive experiment conducted on two real-world datasets shows that our approach generates more precise and insightful explanations compared with baseline approaches.

原文作者：Phung Lai, NhatHai Phan, Han Hu, Anuja Badeti, David Newman, Dejing Dou

原文地址：https://arxiv.org/abs/2004.00204