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 Named Entity Recognition (DS-NER) effectively alleviatesthe burden of annotation, but meanwhile suffers from the label noise. Recentworks attempt to adopt the teacher-student framework to gradually refine thetraining labels and improve the overall robustness. However, we argue thatthese teacher-student methods achieve limited performance because poor networkcalibration produces incorrectly pseudo-labeled samples, leading to errorpropagation. Therefore, we attempt to mitigate this issue by proposing: (1)Uncertainty-aware Teacher Learning that leverages the prediction uncertainty toguide the selection of pseudo-labels, avoiding the number of incorrectpseudo-labels in the self-training stage. (2) Student-student CollaborativeLearning that allows the transfer of reliable labels between two studentnetworks instead of completely relying on all pseudo-labels from its teacher.Meanwhile, this approach allows a full exploration of mislabeled samples ratherthan simply filtering unreliable pseudo-labeled samples. Extensive experimentalresults on five DS-NER datasets demonstrate that our method is superior tostate-of-the-art teacher-student methods.

Distantly-Supervised Named Entity Recognition with Uncertainty-aware Teacher Learning and Student-student Collaborative Learning