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

Entity-relation extraction aims to jointly solve named entity recognition(NER) and relation extraction (RE). Recent approaches use either one-waysequential information propagation in a pipeline manner or two-way implicitinteraction with a shared encoder. However, they still suffer from poorinformation interaction due to the gap between the different task forms of NERand RE, raising a controversial question whether RE is really beneficial toNER. Motivated by this, we propose a novel and unified cascade framework thatcombines the advantages of both sequential information propagation and implicitinteraction. Meanwhile, it eliminates the gap between the two tasks byreformulating entity-relation extraction as unified span-extraction tasks.Specifically, we propose a selection recurrent network as a shared encoder toencode task-specific independent and shared representations and design twosequential information propagation strategies to realize the sequentialinformation flow between NER and RE. Extensive experiments demonstrate that ourapproaches can achieve state-of-the-art results on two common benchmarks, ACE05and SciERC, and effectively model the multi-task interaction, which realizessignificant mutual benefits of NER and RE.

Towards Effective Multi-Task Interaction for Entity-Relation Extraction: A Unified Framework with Selection Recurrent Network