Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explanations for Text (CAT) which provides contrastive explanations for natural language text data with a novel twist as we build and exploit attribute classifiers leading to more semantically meaningful explanations. To ensure that our contrastive generated text has the fewest possible edits with respect to the original text, while also being fluent and close to a human generated contrastive, we resort to a minimal perturbation approach regularized using a BERT language model and attribute classifiers trained on available attributes. We show through qualitative examples and a user study that our method not only conveys more insight because of these attributes, but also leads to better quality (contrastive) text. Moreover, quantitatively we show that our method is more efficient than other state-of-the-art methods with it also scoring higher on benchmark metrics such as flip rate, (normalized) Levenstein distance, fluency and content preservation.

中文翻译：

---

让 CAT 摆脱困境：文本的对比属性解释

用于理解黑盒模型行为的对比解释最近引起了很多关注，因为它们提供了追索的潜力。在本文中，我们提出了一种文本对比属性解释 (CAT) 方法，该方法在我们构建和利用属性分类器以产生更具语义意义的解释时，以新颖的方式为自然语言文本数据提供对比解释。为了确保我们的对比生成的文本相对于原始文本进行最少的编辑，同时流畅并接近人工生成的对比，我们采用了最小扰动方法，使用 BERT 语言模型和在可用数据上训练的属性分类器进行正则化属性。我们通过定性示例和用户研究表明，由于这些属性，我们的方法不仅传达了更多的洞察力，而且还产生了更好的质量（对比）文本。此外，我们从数量上表明，我们的方法比其他最先进的方法更有效，它在基准指标（例如翻转率、（标准化）Levenstein 距离、流畅性和内容保留）上的得分也更高。