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 one of the best studied tasks in naturallanguage processing. However, most approaches are not capable of handlingnested structures which are common in many applications. In this paper weintroduce a novel neural network architecture that first merges tokens and/orentities into entities forming nested structures, and then labels each of themindependently. Unlike previous work, our merge and label approach predictsreal-valued instead of discrete segmentation structures, which allow it tocombine word and nested entity embeddings while maintaining differentiability.%which smoothly groups entities into single vectors across multiple levels. Weevaluate our approach using the ACE 2005 Corpus, where it achievesstate-of-the-art F1 of 74.6, further improved with contextual embeddings (BERT)to 82.4, an overall improvement of close to 8 F1 points over previousapproaches trained on the same data. Additionally we compare it againstBiLSTM-CRFs, the dominant approach for flat NER structures, demonstrating thatits ability to predict nested structures does not impact performance in simplercases.

Merge and Label: A novel neural network architecture for nested NER