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) is a well and widely studied task in naturallanguage processing. Recently, the nested NER has attracted more attentionsince its practicality and difficulty. Existing works for nested NER ignore therecognition order and boundary position relation of nested entities. To addressthese issues, we propose a novel seq2seq model named GPRL, which formulates thenested NER task as an entity triplet sequence generation process. GPRL adoptsthe reinforcement learning method to generate entity triplets decoupling theentity order in gold labels and expects to learn a reasonable recognition orderof entities via trial and error. Based on statistics of boundary distance fornested entities, GPRL designs a Gaussian prior to represent the boundarydistance distribution between nested entities and adjust the output probabilitydistribution of nested boundary tokens. Experiments on three nested NERdatasets demonstrate that GPRL outperforms previous nested NER models.

Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition