arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04837cs.CLcs.LG
收藏

通过概念实现具体化

Rationalization through Concepts

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Diego Antognini, Boi Faltings

摘要:

自动化预测需要人类可以解释的解释。一种类型的解释是理由,即,输入特征的选择,例如模型计算结果的相关文本片段。然而,单一的总体选择并不能提供完整的解释,例如,权衡几个方面来做决定。为此,我们提出了一种新的自我解释模型称为ConRAT。受人类对高层决策的解释通常基于关键概念的启发,ConRAT提取了一组文本片段作为概念,并推断出文档中描述了哪些概念。然后,它用概念的线性聚合来解释结果。两个正则化器驱动ConRAT构建可解释的概念。此外,我们提出了两种技术,以进一步提高的理由和预测性能。在单方面和多方面情感分类任务上的实验表明,ConRAT是第一个在仅使用整体标签的情况下生成与人类合理化相一致的概念的方法。此外,它优于在每个方面标签上独立训练的最先进的方法。

英文摘要:

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a single overall selection does not provide a complete explanation, e.g., weighing several aspects for decisions. To this end, we present a novel self-interpretable model called ConRAT. Inspired by how human explanations for high-level decisions are often based on key concepts, ConRAT extracts a set of text snippets as concepts and infers which ones are described in the document. Then, it explains the outcome with a linear aggregation of concepts. Two regularizers drive ConRAT to build interpretable concepts. In addition, we propose two techniques to boost the rationale and predictive performance further. Experiments on both single- and multi-aspect sentiment classification tasks show that ConRAT is the first to generate concepts that align with human rationalization while using only the overall label. Further, it outperforms state-of-the-art methods trained on each aspect label independently.

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。

↑