Human-Centered Evaluation of Explanations

Jordan Boyd-Graber, Samuel Carton, Shi Feng, Q. Vera Liao, Tania Lombrozo, Alison Smith-Renner, Chenhao Tan


Abstract
The NLP community are increasingly interested in providing explanations for NLP models to help people make sense of model behavior and potentially improve human interaction with models. In addition to computational challenges in generating these explanations, evaluations of the generated explanations require human-centered perspectives and approaches. This tutorial will provide an overview of human-centered evaluations of explanations. First, we will give a brief introduction to the psychological foundation of explanations as well as types of NLP model explanations and their corresponding presentation, to provide the necessary background. We will then present a taxonomy of human-centered evaluation of explanations and dive into depth in the two categories: 1) evaluation based on human-annotated explanations; 2) evaluation with human-subjects studies. We will conclude by discussing future directions. We will also adopt a flipped format to maximize the in- teractive components for the live audience.
Anthology ID:
2022.naacl-tutorials.4
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Miguel Ballesteros, Yulia Tsvetkov, Cecilia O. Alm
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
26–32
Language:
URL:
https://aclanthology.org/2022.naacl-tutorials.4
DOI:
10.18653/v1/2022.naacl-tutorials.4
Bibkey:
Cite (ACL):
Jordan Boyd-Graber, Samuel Carton, Shi Feng, Q. Vera Liao, Tania Lombrozo, Alison Smith-Renner, and Chenhao Tan. 2022. Human-Centered Evaluation of Explanations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts, pages 26–32, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Human-Centered Evaluation of Explanations (Boyd-Graber et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-tutorials.4.pdf