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

While sophisticated neural-based techniques have been developed in readingcomprehension, most approaches model the answer in an independent manner,ignoring its relations with other answer candidates. This problem can be evenworse in open-domain scenarios, where candidates from multiple passages shouldbe combined to answer a single question. In this paper, we formulate readingcomprehension as an extract-then-select two-stage procedure. We first extractanswer candidates from passages, then select the final answer by combininginformation from all the candidates. Furthermore, we regard candidateextraction as a latent variable and train the two-stage process jointly withreinforcement learning. As a result, our approach has improved thestate-of-the-art performance significantly on two challenging open-domainreading comprehension datasets. Further analysis demonstrates the effectivenessof our model components, especially the information fusion of all thecandidates and the joint training of the extract-then-select procedure.

Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension