Reasoning with Natural Language Explanations

TL;DR

This paper reviews the role of natural language explanations in reasoning, discussing how explanation-based NLI models can encode complex reasoning and their evaluation methodologies.

Contribution

It provides a comprehensive introduction to explanation-based NLI, covering epistemological foundations, architectural trends, and evaluation methods.

Findings

Explanation-based NLI models enhance reasoning capabilities.

Systematic analysis of architectural approaches for explanatory reasoning.

Evaluation methodologies for explanation quality in NLI systems.

Abstract

Explanation constitutes an archetypal feature of human rationality, underpinning learning and generalisation, and representing one of the media supporting scientific discovery and communication. Due to the importance of explanations in human reasoning, an increasing amount of research in Natural Language Inference (NLI) has started reconsidering the role that explanations play in learning and inference, attempting to build explanation-based NLI models that can effectively encode and use natural language explanations on downstream tasks. Research in explanation-based NLI, however, presents specific challenges and opportunities, as explanatory reasoning reflects aspects of both material and formal inference, making it a particularly rich setting to model and deliver complex reasoning. In this tutorial, we provide a comprehensive introduction to the field of explanation-based NLI, grounding this discussion on the epistemological-linguistic foundations of explanations, systematically describing the main architectural trends and evaluation methodologies that can be used to build systems capable of explanatory reasoning.