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

Generative approaches have been recently shown to be effective for bothEntity Disambiguation and Entity Linking (i.e., joint mention detection anddisambiguation). However, the previously proposed autoregressive formulationfor EL suffers from i) high computational cost due to a complex (deep) decoder,ii) non-parallelizable decoding that scales with the source sequence length,and iii) the need for training on a large amount of data. In this work, wepropose a very efficient approach that parallelizes autoregressive linkingacross all potential mentions and relies on a shallow and efficient decoder.Moreover, we augment the generative objective with an extra discriminativecomponent, i.e., a correction term which lets us directly optimize thegenerator's ranking. When taken together, these techniques tackle all the aboveissues: our model is >70 times faster and more accurate than the previousgenerative method, outperforming state-of-the-art approaches on the standardEnglish dataset AIDA-CoNLL. Source code available athttps://github.com/nicola-decao/efficient-autoregressive-EL

Highly Parallel Autoregressive Entity Linking with Discriminative Correction