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/

Zendy Plus

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

Zendy Tools

Zendy Open

While neural networks with attention mechanisms have achieved superiorperformance on many natural language processing tasks, it remains unclear towhich extent learned attention resembles human visual attention. In this paper,we propose a new method that leverages eye-tracking data to investigate therelationship between human visual attention and neural attention in machinereading comprehension. To this end, we introduce a novel 23 participant eyetracking dataset - MQA-RC, in which participants read movie plots and answeredpre-defined questions. We compare state of the art networks based on longshort-term memory (LSTM), convolutional neural models (CNN) and XLNetTransformer architectures. We find that higher similarity to human attentionand performance significantly correlates to the LSTM and CNN models. However,we show this relationship does not hold true for the XLNet models -- despitethe fact that the XLNet performs best on this challenging task. Our resultssuggest that different architectures seem to learn rather different neuralattention strategies and similarity of neural to human attention does notguarantee best performance.

Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension