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

Deep neural models for named entity recognition (NER) have shown impressiveresults in overcoming label scarcity and generalizing to unseen entities byleveraging distant supervision and auxiliary information such as explanations.However, the costs of acquiring such additional information are generallyprohibitive. In this paper, we present a novel two-stage framework(AutoTriggER) to improve NER performance by automatically generating andleveraging ``entity triggers'' which are human-readable cues in the text thathelp guide the model to make better decisions. Our framework leverages post-hocexplanation to generate rationales and strengthens a model's prior knowledgeusing an embedding interpolation technique. This approach allows models toexploit triggers to infer entity boundaries and types instead of solelymemorizing the entity words themselves. Through experiments on threewell-studied NER datasets, AutoTriggER shows strong label-efficiency, iscapable of generalizing to unseen entities, and outperforms the RoBERTa-CRFbaseline by nearly 0.5 F1 points on average.

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction