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

Distantly supervised (DS) relation extraction (RE) has attracted muchattention in the past few years as it can utilize large-scale auto-labeleddata. However, its evaluation has long been a problem: previous works eithertook costly and inconsistent methods to manually examine a small sample ofmodel predictions, or directly test models on auto-labeled data -- which, byour check, produce as much as 53% wrong labels at the entity pair level in thepopular NYT10 dataset. This problem has not only led to inaccurate evaluation,but also made it hard to understand where we are and what's left to improve inthe research of DS-RE. To evaluate DS-RE models in a more credible way, webuild manually-annotated test sets for two DS-RE datasets, NYT10 and Wiki20,and thoroughly evaluate several competitive models, especially the latestpre-trained ones. The experimental results show that the manual evaluation canindicate very different conclusions from automatic ones, especially someunexpected observations, e.g., pre-trained models can achieve dominatingperformance while being more susceptible to false-positives compared toprevious methods. We hope that both our manual test sets and novel observationscan help advance future DS-RE research.

Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction