Argument & Computation最新文献

Argumentation with justified preferences 论证与合理的偏好

Argument & Computation Pub Date : 2023-10-25 DOI: 10.3233/aac-220012

Sung-Jun Pyon

引用次数: 0

Abstract argumentation with conditional preferences 具有条件偏好的抽象论证

Argument & Computation Pub Date : 2023-07-28 DOI: 10.3233/aac-230001

Michael Bernreiter, Wolfgang Dvořák, Stefan Woltran

引用次数: 0

Argumentative explanations for pattern-based text classifiers 基于模式的文本分类器的论证性解释

Argument & Computation Pub Date : 2023-06-07 DOI: 10.3233/aac-220004

Piyawat Lertvittayakumjorn, Francesca Toni

{"title":"Argumentative explanations for pattern-based text classifiers","authors":"Piyawat Lertvittayakumjorn, Francesca Toni","doi":"10.3233/aac-220004","DOIUrl":"https://doi.org/10.3233/aac-220004","url":null,"abstract":"Recent works in Explainable AI mostly address the transparency issue of black-box models or create explanations for any kind of models (i.e., they are model-agnostic), while leaving explanations of interpretable models largely underexplored. In this paper, we fill this gap by focusing on explanations for a specific interpretable model, namely pattern-based logistic regression (PLR) for binary text classification. We do so because, albeit interpretable, PLR is challenging when it comes to explanations. In particular, we found that a standard way to extract explanations from this model does not consider relations among the features, making the explanations hardly plausible to humans. Hence, we propose AXPLR, a novel explanation method using (forms of) computational argumentation to generate explanations (for outputs computed by PLR) which unearth model agreements and disagreements among the features. Specifically, we use computational argumentation as follows: we see features (patterns) in PLR as arguments in a form of quantified bipolar argumentation frameworks (QBAFs) and extract attacks and supports between arguments based on specificity of the arguments; we understand logistic regression as a gradual semantics for these QBAFs, used to determine the arguments’ dialectic strength; and we study standard properties of gradual semantics for QBAFs in the context of our argumentative re-interpretation of PLR, sanctioning its suitability for explanatory purposes. We then show how to extract intuitive explanations (for outputs computed by PLR) from the constructed QBAFs. Finally, we conduct an empirical evaluation and two experiments in the context of human-AI collaboration to demonstrate the advantages of our resulting AXPLR method.","PeriodicalId":44268,"journal":{"name":"Argument & Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135364371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inferring attack relations for gradual semantics 渐进式语义的推理攻击关系

Argument & Computation Pub Date : 2023-04-20 DOI: 10.3233/aac-220010

Nir Oren, Bruno Yun

引用次数: 0