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

Bodhisattwa Prasad Majumder, Oana Camburu, Thomas Lukasiewicz, Julian Mcauley
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:14786-14801, 2022.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-majumder22a, title = {Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations}, author = {Majumder, Bodhisattwa Prasad and Camburu, Oana and Lukasiewicz, Thomas and Mcauley, Julian}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {14786--14801}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/majumder22a/majumder22a.pdf}, url = {https://proceedings.mlr.press/v162/majumder22a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations %A Bodhisattwa Prasad Majumder %A Oana Camburu %A Thomas Lukasiewicz %A Julian Mcauley %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-majumder22a %I PMLR %P 14786--14801 %U https://proceedings.mlr.press/v162/majumder22a.html %V 162 %X 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.
APA
Majumder, B.P., Camburu, O., Lukasiewicz, T. & Mcauley, J.. (2022). Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:14786-14801 Available from https://proceedings.mlr.press/v162/majumder22a.html.

Related Material