Counterfactual Variable Control for Robust and Interpretable Question Answering

Cited by: 0|Bibtex|Views18
Other Links: arxiv.org

Abstract:

Deep neural network based question answering (QA) models are neither robust nor explainable in many cases. For example, a multiple-choice QA model, tested without any input of question, is surprisingly "capable" to predict the most of correct options. In this paper, we inspect such spurious "capability" of QA models using causal inferen...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments