Rationalization is a self-explaining framework for NLP models. Conventional work typically uses the maximum mutual information (MMI) criterion to find the rationale that is most indicative of the target label. However, this criterion can be influenced by spurious features that correlate with the causal rationale or the target label. Instead of attempting to rectify the issues of the MMI criterion, we propose a novel criterion to uncover the causal rationale, termed the Minimum Conditional Dependence (MCD) criterion, which is grounded on our finding that the non-causal features and the target label are \emph{d-separated} by the causal rationale. By minimizing the dependence between the unselected parts of the input and the target label conditioned on the selected rationale candidate, all the causes of the label are compelled to be selected. In this study, we employ a simple and practical measure of dependence, specifically the KL-divergence, to validate our proposed MCD criterion. Empirically, we demonstrate that MCD improves the F1 score by up to $13.7\%$ compared to previous state-of-the-art MMI-based methods. Our code is available at: \url{https://github.com/jugechengzi/Rationalization-MCD}.

翻译：理性化是NLP模型的一种自解释框架。传统工作通常采用最大互信息（MMI）准则来寻找最能指示目标标签的理由。然而，该准则可能受到与因果理由或目标标签相关的虚假特征的影响。我们并未试图修正MMI准则的缺陷，而是提出了一种新的基于因果理由的准则——最小条件依赖（MCD）准则，其基础在于我们的发现：非因果特征与目标标签通过因果理由实现了*d分离*。通过最小化未选择输入部分与目标标签在选定理由候选条件下的依赖关系，标签的所有原因均被强制选择。本研究采用简单实用的依赖度量（即KL散度）来验证提出的MCD准则。实验表明，与先前基于MMI的最先进方法相比，MCD将F1分数提升了高达13.7%。我们的代码已开源：https://github.com/jugechengzi/Rationalization-MCD。