论文标题
一次（反事实）差异一次
Making a (Counterfactual) Difference One Rationale at a Time
论文作者
论文摘要
理由是解释推论的提取文本片段，已成为可解释的自然语言处理（NLP）的流行框架。理由模型通常由两个合作模块组成：一个选择器和一个分类器，其目的是在“选定”文本和文档标签之间最大化互信息（MMI）。尽管有承诺，但基于MMI的方法通常会采用虚假的文本模式，并导致具有荒谬行为的模型。在这项工作中，我们研究反事实数据增强（CDA）是否没有人为援助，可以通过降低虚假信号和文档标签之间的相互信息来提高选择器的性能。我们的反事实是使用依赖类的生成模型以无监督的方式生产的。从信息理论镜头中，我们得出了我们的CDA方法将成功的未表现数据集的属性。通过与多个基线进行比较，包括在两个多方面数据集上进行改进的基于MMI的理性模式，从而在经验上评估了CDA的有效性。我们的结果表明，CDA产生的原理可以更好地捕获感兴趣的信号。
Rationales, snippets of extracted text that explain an inference, have emerged as a popular framework for interpretable natural language processing (NLP). Rationale models typically consist of two cooperating modules: a selector and a classifier with the goal of maximizing the mutual information (MMI) between the "selected" text and the document label. Despite their promises, MMI-based methods often pick up on spurious text patterns and result in models with nonsensical behaviors. In this work, we investigate whether counterfactual data augmentation (CDA), without human assistance, can improve the performance of the selector by lowering the mutual information between spurious signals and the document label. Our counterfactuals are produced in an unsupervised fashion using class-dependent generative models. From an information theoretic lens, we derive properties of the unaugmented dataset for which our CDA approach would succeed. The effectiveness of CDA is empirically evaluated by comparing against several baselines including an improved MMI-based rationale schema on two multi aspect datasets. Our results show that CDA produces rationales that better capture the signal of interest.
