Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
复制标题
DOI：
--
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Bodhisattwa Prasad Majumder;Oana-Maria Camburu;Thomas Lukasiewicz;Julian McAuley
中科院分区：
文献类型：
--
作者：
Bodhisattwa Prasad Majumder;Oana-Maria Camburu;Thomas Lukasiewicz;Julian McAuley
生成提取依据的模型（即，特征子集）或自然语言解释（NLE）的预测对于可解释的人工智能非常重要。虽然提取的基本原理提供了对预测最负责任的特征的快速视图，但NLE允许对预测背后的决策过程进行全面描述。然而，目前的模型，产生最好的提取原理或NLE往往落后于国家的最先进的（SOTA）的任务性能。在这项工作中，我们通过引入RExC来弥合这一差距，RExC是一个自我合理化的框架，它的预测和两种互补类型的解释（NLE和提取理性）在背景知识中。我们的框架通过以下方式改进了以前的方法：（i）在提供解释的同时达到SOTA任务性能，（ii）提供两种类型的解释，而现有模型通常只提供一种类型，以及（iii）在两种类型的解释质量方面大幅击败以前的SOTA。此外，在RExC的扰动分析表明，解释和预测之间的高度关联，忠实的解释的必要属性。
Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing RExC, a self-rationalizing framework that grounds its predictions and two complementary types of explanations (NLEs and extractive rationales) in background knowledge. Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations. Furthermore, a perturbation analysis in RExC shows a high degree of association between explanations and predictions, a necessary property of faithful explanations.