Towards human-compatible XAI: Explaining data differentials with concept induction over background knowledge

IF 2.1 3区计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Journal of Web Semantics Pub Date : 2023-09-26 DOI:10.1016/j.websem.2023.100807

Cara Leigh Widmer , Md Kamruzzaman Sarker , Srikanth Nadella , Joshua Fiechter , Ion Juvina , Brandon Minnery , Pascal Hitzler , Joshua Schwartz , Michael Raymer

{"title":"Towards human-compatible XAI: Explaining data differentials with concept induction over background knowledge","authors":"Cara Leigh Widmer , Md Kamruzzaman Sarker , Srikanth Nadella , Joshua Fiechter , Ion Juvina , Brandon Minnery , Pascal Hitzler , Joshua Schwartz , Michael Raymer","doi":"10.1016/j.websem.2023.100807","DOIUrl":null,"url":null,"abstract":"<div><p>Concept induction, which is based on formal logical reasoning over description logics<span>, has been used in ontology engineering<span><span> in order to create ontology (TBox) axioms from the base data (ABox) graph. In this paper, we show that it can also be used to explain data differentials, for example in the context of Explainable AI (XAI), and we show that it can in fact be done in a way that is meaningful to a human observer. Our approach utilizes a large class hierarchy, curated from the Wikipedia category hierarchy, as background knowledge. To make the explanations easily understandable for non-specialists, the complex description logic explanations generated by our concept </span>induction system (ECII) were presented as a word list consisting of the concept names occurring in the highest rated system responses.</span></span></p></div>","PeriodicalId":49951,"journal":{"name":"Journal of Web Semantics","volume":"79 ","pages":"Article 100807"},"PeriodicalIF":2.1000,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Web Semantics","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1570826823000367","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Concept induction, which is based on formal logical reasoning over description logics, has been used in ontology engineering in order to create ontology (TBox) axioms from the base data (ABox) graph. In this paper, we show that it can also be used to explain data differentials, for example in the context of Explainable AI (XAI), and we show that it can in fact be done in a way that is meaningful to a human observer. Our approach utilizes a large class hierarchy, curated from the Wikipedia category hierarchy, as background knowledge. To make the explanations easily understandable for non-specialists, the complex description logic explanations generated by our concept induction system (ECII) were presented as a word list consisting of the concept names occurring in the highest rated system responses.

查看原文本刊更多论文

面向人类兼容的XAI:用背景知识的概念归纳法解释数据差异

概念归纳法是一种基于形式逻辑推理而不是描述逻辑的方法，它被用于本体工程中，以便从基础数据图(ABox)中创建本体公理。在本文中，我们展示了它也可以用来解释数据差异，例如在可解释人工智能(XAI)的背景下，我们展示了它实际上可以以一种对人类观察者有意义的方式完成。我们的方法利用了一个大的类层次结构，从维基百科分类层次结构中提取，作为背景知识。为了使非专业人士更容易理解这些解释，我们的概念归纳系统(ECII)生成的复杂描述逻辑解释以单词列表的形式呈现，其中包含出现在评分最高的系统反应中的概念名称。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Web Semantics 工程技术-计算机：人工智能

CiteScore

6.20

自引率

12.00%

发文量

审稿时长

14.6 weeks

期刊介绍： The Journal of Web Semantics is an interdisciplinary journal based on research and applications of various subject areas that contribute to the development of a knowledge-intensive and intelligent service Web. These areas include: knowledge technologies, ontology, agents, databases and the semantic grid, obviously disciplines like information retrieval, language technology, human-computer interaction and knowledge discovery are of major relevance as well. All aspects of the Semantic Web development are covered. The publication of large-scale experiments and their analysis is also encouraged to clearly illustrate scenarios and methods that introduce semantics into existing Web interfaces, contents and services. The journal emphasizes the publication of papers that combine theories, methods and experiments from different subject areas in order to deliver innovative semantic methods and applications.