Ontology-based Interpretable Machine Learning for Textual Data
Ontology-based Interpretable Machine Learning for Textual Data
复制标题
DOI：
10.1109/ijcnn48605.2020.9206753
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Phung Lai;Nhathai Phan;Han Hu;Anuja Badeti;David Newman;D. Dou
中科院分区：
文献类型：
--
作者：
Phung Lai;Nhathai Phan;Han Hu;Anuja Badeti;David Newman;D. Dou
在本文中，我们介绍了一种新的解释框架，该框架基于基于本体的采样技术学习可解释模型来解释不可知性预测模型。与现有的方法不同，我们的算法考虑了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，我们设计了一个可学习的锚点算法，以更好地在本地提取解释。进一步介绍了一组关于将学习的可解释表示与锚点相结合以生成可理解的语义解释的规则。在两个真实世界数据集上进行的广泛实验表明，与基准方法相比，我们的方法生成了更准确和更有洞察力的解释。
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.