Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System

Barbara Rychalska, Dominika Basaj, Anna Wróblewska, Przemyslaw Biecek


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.
Anthology ID:
W18-5436
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
322–324
Language:
URL:
https://aclanthology.org/W18-5436
DOI:
10.18653/v1/W18-5436
Bibkey:
Cite (ACL):
Barbara Rychalska, Dominika Basaj, Anna Wróblewska, and Przemyslaw Biecek. 2018. Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 322–324, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System (Rychalska et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5436.pdf