A survey on improving NLP models with human explanations

TL;DR

This survey reviews various methods of enhancing NLP models using human explanations, highlighting their benefits, differences, and guiding principles for selecting appropriate techniques for specific applications.

Contribution

It provides a comprehensive overview of existing methods for learning from human explanations in NLP and discusses factors influencing their selection.

Findings

Learning from explanations improves data efficiency and performance.

Different explanation types and integration mechanisms exist and are rarely compared.

Guidelines are provided for choosing suitable methods based on use-case factors.

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.