Reasoning with Natural Language Explanations

Marco Valentino, André Freitas


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.
Anthology ID:
2024.emnlp-tutorials.4
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Jessy Li, Fei Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–31
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.emnlp-tutorials.4/
DOI:
10.18653/v1/2024.emnlp-tutorials.4
Bibkey:
Cite (ACL):
Marco Valentino and André Freitas. 2024. Reasoning with Natural Language Explanations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 25–31, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Reasoning with Natural Language Explanations (Valentino & Freitas, EMNLP 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.emnlp-tutorials.4.pdf