Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

By Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz, Julian McAuley. 2021

40 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Thomas Lukasiewicz
2. Oana-Maria Camburu
3. Yordan Yordanov
4. Vid Kocijan
5. Ana Marasovic
6. Sarah Wiegreffe
7. Chenhao Tan
8. Mohit Bansal

In Natural Language Processing

1. Yordan Yordanov
2. Vid Kocijan
3. Thomas Lukasiewicz
4. Oana-Maria Camburu
5. Ana Marasovic
6. Sarah Wiegreffe
7. Kyunghyun Cho
8. Mohit Bansal

In Safety, Robustness & Interpretability

1. Thomas Lukasiewicz
2. Oana-Maria Camburu

Citations in the corpus

• Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations (2021, methodology): “Commonsense Validation and Explanation (ComVE) (Wang et al., 2020), as reformulated by Majumder et al. (2022), is the task of jointly identifying which one of two statements contradicts commonsense and explaining why.”