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 systems achieve remarkable performance on domainssuch as English news. It is natural to ask: What are these models actuallylearning to achieve this? Are they merely memorizing the names themselves? Orare they capable of interpreting the text and inferring the correct entity typefrom the linguistic context? We examine these questions by contrasting theperformance of several variants of LSTM-CRF architectures for named entityrecognition, with some provided only representations of the context asfeatures. We also perform similar experiments for BERT. We find that contextrepresentations do contribute to system performance, but that the main factordriving high performance is learning the name tokens themselves. We enlisthuman annotators to evaluate the feasibility of inferring entity types from thecontext alone and find that, while people are not able to infer the entity typeeither for the majority of the errors made by the context-only system, there issome room for improvement. A system should be able to recognize any name in apredictive context correctly and our experiments indicate that current systemsmay be further improved by such capability.

Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve