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

Sequential labeling-based NER approaches restrict each word belonging to atmost one entity mention, which will face a serious problem when recognizingnested entity mentions. In this paper, we propose to resolve this problem bymodeling and leveraging the head-driven phrase structures of entity mentions,i.e., although a mention can nest other mentions, they will not share the samehead word. Specifically, we propose Anchor-Region Networks (ARNs), asequence-to-nuggets architecture for nested mention detection. ARNs firstidentify anchor words (i.e., possible head words) of all mentions, and thenrecognize the mention boundaries for each anchor word by exploiting regularphrase structures. Furthermore, we also design Bag Loss, an objective functionwhich can train ARNs in an end-to-end manner without using any anchor wordannotation. Experiments show that ARNs achieve the state-of-the-art performanceon three standard nested entity mention detection benchmarks.

Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks