arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.13653cs.CLcs.AI
收藏

通过词属性解释类

Explaining Classes through Word Attribution

University of Turku(图尔库大学)

Samuel Rönnqvist, Amanda Myntti, Aki-Juhani Kyröläinen, Sampo Pyysalo, Veronika Laippala, Filip Ginter

摘要:

近年来,已经提出了几种方法来解释深度学习模型的单个预测,但很少有人研究如何聚合这些预测来解释这些模型如何在文本分类任务中将类视为一个整体。在这项工作中,我们提出了一种使用深度学习模型和集成特征属性技术来解释类的方法,该方法通过将文本分类中单个示例的解释聚合到类的一般描述中。我们展示了使用XML-R模型和英语在线注册语料库(CORE)的Web寄存器(体裁)分类的方法,发现该方法确定合理的和歧视性的关键字特征,但最小的类。

英文摘要:

In recent years, several methods have been proposed for explaining individual predictions of deep learning models, yet there has been little study of how to aggregate these predictions to explain how such models view classes as a whole in text classification tasks. In this work, we propose a method for explaining classes using deep learning models and the Integrated Gradients feature attribution technique by aggregating explanations of individual examples in text classification to general descriptions of the classes. We demonstrate the approach on Web register (genre) classification using the XML-R model and the Corpus of Online Registers of English (CORE), finding that the method identifies plausible and discriminative keywords characterizing all but the smallest class.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑