A survey on improving NLP models with human explanations

Mareike Hartmann, Daniel Sonntag


Abstract
Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from explanations a promising way to establish a fruitful human-machine interaction. Several methods have been proposed for improving natural language processing (NLP) models with human explanations, that rely on different explanation types and mechanism for integrating these explanations into the learning process. These methods are rarely compared with each other, making it hard for practitioners to choose the best combination of explanation type and integration mechanism for a specific use-case. In this paper, we give an overview of different methods for learning from human explanations, and discuss different factors that can inform the decision of which method to choose for a specific use-case.
Anthology ID:
2022.lnls-1.5
Volume:
Proceedings of the First Workshop on Learning with Natural Language Supervision
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Jacob Andreas, Karthik Narasimhan, Aida Nematzadeh
Venue:
LNLS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–47
Language:
URL:
https://aclanthology.org/2022.lnls-1.5
DOI:
10.18653/v1/2022.lnls-1.5
Bibkey:
Cite (ACL):
Mareike Hartmann and Daniel Sonntag. 2022. A survey on improving NLP models with human explanations. In Proceedings of the First Workshop on Learning with Natural Language Supervision, pages 40–47, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
A survey on improving NLP models with human explanations (Hartmann & Sonntag, LNLS 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lnls-1.5.pdf
Video:
 https://aclanthology.org/2022.lnls-1.5.mp4
Data
e-SNLI