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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The state-of-the-art named entity recognition (NER) systems are statisticalmachine learning models that have strong generalization capability (i.e., canrecognize unseen entities that do not appear in training data) based on lexicaland contextual information. However, such a model could still make mistakes ifits features favor a wrong entity type. In this paper, we utilize Wikipedia asan open knowledge base to improve multilingual NER systems. Central to ourapproach is the construction of high-accuracy, high-coverage multilingualWikipedia entity type mappings. These mappings are built from weakly annotateddata and can be extended to new languages with no human annotation orlanguage-dependent knowledge involved. Based on these mappings, we developseveral approaches to improve an NER system. We evaluate the performance of theapproaches via experiments on NER systems trained for 6 languages. Experimentalresults show that the proposed approaches are effective in improving theaccuracy of such systems on unseen entities, especially when a system isapplied to a new domain or it is trained with little training data (up to 18.3F1 score improvement).

Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping