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/

Zendy Plus

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

Zendy Tools

Zendy Open

In recent years there is a surge of interest in applying distant supervision(DS) to automatically generate training data for relation extraction (RE). Inthis paper, we study the problem what limits the performance of DS-trainedneural models, conduct thorough analyses, and identify a factor that caninfluence the performance greatly, shifted label distribution. Specifically, wefound this problem commonly exists in real-world DS datasets, and withoutspecial handing, typical DS-RE models cannot automatically adapt to this shift,thus achieving deteriorated performance. To further validate our intuition, wedevelop a simple yet effective adaptation method for DS-trained models, biasadjustment, which updates models learned over the source domain (i.e., DStraining set) with a label distribution estimated on the target domain (i.e.,test set). Experiments demonstrate that bias adjustment achieves consistentperformance gains on DS-trained models, especially on neural models, with an upto 23% relative F1 improvement, which verifies our assumptions. Our code anddata can be found at\url{https://github.com/INK-USC/shifted-label-distribution}.

Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction