基于超立方体的符号知识抽取方法的统一模型研究

IF 1.9 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Intelligenza Artificiale Pub Date : 2023-06-07 DOI:10.3233/IA-230001
Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini
{"title":"基于超立方体的符号知识抽取方法的统一模型研究","authors":"Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini","doi":"10.3233/IA-230001","DOIUrl":null,"url":null,"abstract":"The XAI community is currently studying and developing symbolic knowledge-extraction (SKE) algorithms as a means to produce human-intelligible explanations for black-box machine learning predictors, so as to achieve believability in human-machine interaction. However, many extraction procedures exist in the literature, and choosing the most adequate one is increasingly cumbersome, as novel methods keep on emerging. Challenges arise from the fact that SKE algorithms are commonly defined based on theoretical assumptions that typically hinder practical applicability. This paper focuses on hypercube-based SKE methods, a quite general class of extraction techniques mostly devoted to regression-specific tasks. We first show that hypercube-based methods are flexible enough to support classification problems as well, then we propose a general model for them, and discuss how they support SKE on datasets, predictors, or learning tasks of any sort. Empirical examples are reported as well –based upon the PSyKE framework –, showing the applicability of hypercube-based methods to actual classification tasks.","PeriodicalId":42055,"journal":{"name":"Intelligenza Artificiale","volume":"17 1","pages":"63-75"},"PeriodicalIF":1.9000,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Towards a unified model for symbolic knowledge extraction with hypercube-based methods\",\"authors\":\"Federico Sabbatini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini\",\"doi\":\"10.3233/IA-230001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The XAI community is currently studying and developing symbolic knowledge-extraction (SKE) algorithms as a means to produce human-intelligible explanations for black-box machine learning predictors, so as to achieve believability in human-machine interaction. However, many extraction procedures exist in the literature, and choosing the most adequate one is increasingly cumbersome, as novel methods keep on emerging. Challenges arise from the fact that SKE algorithms are commonly defined based on theoretical assumptions that typically hinder practical applicability. This paper focuses on hypercube-based SKE methods, a quite general class of extraction techniques mostly devoted to regression-specific tasks. We first show that hypercube-based methods are flexible enough to support classification problems as well, then we propose a general model for them, and discuss how they support SKE on datasets, predictors, or learning tasks of any sort. Empirical examples are reported as well –based upon the PSyKE framework –, showing the applicability of hypercube-based methods to actual classification tasks.\",\"PeriodicalId\":42055,\"journal\":{\"name\":\"Intelligenza Artificiale\",\"volume\":\"17 1\",\"pages\":\"63-75\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2023-06-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Intelligenza Artificiale\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3233/IA-230001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intelligenza Artificiale","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3233/IA-230001","RegionNum":0,"RegionCategory":null,"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

摘要

XAI社区目前正在研究和开发符号知识提取(SKE)算法,作为为黑箱机器学习预测器生成人类可理解的解释的手段,从而实现人机交互的可信度。然而,文献中存在许多提取方法,随着新方法的不断涌现,选择最合适的方法变得越来越麻烦。挑战来自这样一个事实,即SKE算法通常是基于理论假设来定义的,这通常会阻碍实际应用。本文主要关注基于超立方体的SKE方法,这是一种非常通用的提取技术,主要用于特定于回归的任务。我们首先展示了基于超立方体的方法足够灵活,也可以支持分类问题,然后我们为它们提出了一个通用模型,并讨论了它们如何在数据集、预测器或任何类型的学习任务上支持SKE。还报告了基于PSyKE框架的经验示例,显示了基于超立方体的方法对实际分类任务的适用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Towards a unified model for symbolic knowledge extraction with hypercube-based methods
The XAI community is currently studying and developing symbolic knowledge-extraction (SKE) algorithms as a means to produce human-intelligible explanations for black-box machine learning predictors, so as to achieve believability in human-machine interaction. However, many extraction procedures exist in the literature, and choosing the most adequate one is increasingly cumbersome, as novel methods keep on emerging. Challenges arise from the fact that SKE algorithms are commonly defined based on theoretical assumptions that typically hinder practical applicability. This paper focuses on hypercube-based SKE methods, a quite general class of extraction techniques mostly devoted to regression-specific tasks. We first show that hypercube-based methods are flexible enough to support classification problems as well, then we propose a general model for them, and discuss how they support SKE on datasets, predictors, or learning tasks of any sort. Empirical examples are reported as well –based upon the PSyKE framework –, showing the applicability of hypercube-based methods to actual classification tasks.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Intelligenza Artificiale
Intelligenza Artificiale COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
3.50
自引率
6.70%
发文量
13
期刊最新文献
Special Issue NL4AI 2022: Workshop on natural language for artificial intelligence User-centric item characteristics for personalized multimedia systems: A systematic review Combining human intelligence and machine learning for fact-checking: Towards a hybrid human-in-the-loop framework A framework for safe decision making: A convex duality approach Grounding End-to-End Pre-trained architectures for Semantic Role Labeling in multiple languages
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1