As deep neural models in NLP become more complex, and as a consequence opaque, the necessity to interpret them becomes greater. A burgeoning interest has emerged in rationalizing explanations to provide short and coherent justifications for predictions. In this position paper, we advocate for a formal framework for key concepts and properties about rationalizing explanations to support their evaluation systematically. We also outline one such formal framework, tailored to rationalizing explanations of increasingly complex structures, from free-form explanations to deductive explanations, to argumentative explanations (with the richest structure). Focusing on the automated fact verification task, we provide illustrations of the use and usefulness of our formalization for evaluating explanations, tailored to their varying structures.

翻译：随着自然语言处理中的深度神经模型日益复杂，进而变得不透明，对它们进行解释的需求也愈发迫切。一种新兴的研究兴趣聚焦于通过合理解释来提供对预测的简洁、连贯的论证。在这篇立场论文中，我们主张建立一个关于合理解释的关键概念与属性的形式化框架，以支持对其的系统性评估。我们概述了这样一个形式化框架，专门面向结构日益复杂的合理解释——从自由形式的解释，到演绎性解释，再到论证性解释（结构最为丰富）。以自动化事实核查任务为例，我们展示了该形式化方法在评估不同结构解释时的实际用途与价值。