English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper we present the results of an investigation of the importance ofverbs in a deep learning QA system trained on SQuAD dataset. We show that mainverbs in questions carry little influence on the decisions made by the system -in over 90% of researched cases swapping verbs for their antonyms did notchange system decision. We track this phenomenon down to the insides of thenet, analyzing the mechanism of self-attention and values contained in hiddenlayers of RNN. Finally, we recognize the characteristics of the SQuAD datasetas the source of the problem. Our work refers to the recently popular topic ofadversarial examples in NLP, combined with investigating deep net structure.

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