A survey on improving NLP models with human explanations
It addresses the problem for NLP practitioners in selecting effective explanation-based methods, but is incremental as it reviews existing approaches without new empirical results.
The paper surveys methods for improving NLP models by incorporating human explanations to enhance data efficiency and performance, but notes a lack of comparative analysis among these methods.
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.