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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a framework for question answering that can efficiently scale tolonger documents while maintaining or even improving performance ofstate-of-the-art models. While most successful approaches for readingcomprehension rely on recurrent neural networks (RNNs), running them over longdocuments is prohibitively slow because it is difficult to parallelize oversequences. Inspired by how people first skim the document, identify relevantparts, and carefully read these parts to produce an answer, we combine acoarse, fast model for selecting relevant sentences and a more expensive RNNfor producing the answer from those sentences. We treat sentence selection as alatent variable trained jointly from the answer only using reinforcementlearning. Experiments demonstrate the state of the art performance on achallenging subset of the Wikireading and on a new dataset, while speeding upthe model by 3.5x-6.7x.

Hierarchical Question Answering for Long Documents