Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System
Abstract
In this paper we present the results of an investigation of the importance of verbs in a deep learning QA system trained on SQuAD dataset. We show that main verbs in questions carry little influence on the decisions made by the system - in over 90% of researched cases swapping verbs for their antonyms did not change system decision. We track this phenomenon down to the insides of the net, analyzing the mechanism of self-attention and values contained in hidden layers of RNN. Finally, we recognize the characteristics of the SQuAD dataset as the source of the problem. Our work refers to the recently popular topic of adversarial examples in NLP, combined with investigating deep net structure.
Keywords
Cite
@article{arxiv.1809.03740,
title = {Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System},
author = {Barbara Rychalska and Dominika Basaj and Przemyslaw Biecek and Anna Wroblewska},
journal= {arXiv preprint arXiv:1809.03740},
year = {2022}
}
Comments
Accepted to Analyzing and interpreting neural networks for NLP workshop at EMNLP 2018