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

Named Entity Recognition (NER) systems often demonstrate great performance onin-distribution data, but perform poorly on examples drawn from a shifteddistribution. One way to evaluate the generalization ability of NER models isto use adversarial examples, on which the specific variations associated withnamed entities are rarely considered. To this end, we propose leveragingexpert-guided heuristics to change the entity tokens and their surroundingcontexts thereby altering their entity types as adversarial attacks. Usingexpert-guided heuristics, we augmented the CoNLL 2003 test set and manuallyannotated it to construct a high-quality challenging set. We found thatstate-of-the-art NER systems trained on CoNLL 2003 training data dropperformance dramatically on our challenging set. By training on adversarialaugmented training examples and using mixup for regularization, we were able tosignificantly improve the performance on the challenging set as well as improveout-of-domain generalization which we evaluated by using OntoNotes data. Wehave publicly released our dataset and code athttps://github.com/GT-SALT/Guided-Adversarial-Augmentation.

Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition