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) aims to locate entitymentions and classify their types with only knowledge bases or gazetteers andunlabeled corpus. However, distant annotations are noisy and degrade theperformance of NER models. In this paper, we propose a noise-robust prototypenetwork named MProto for the DS-NER task. Different from previousprototype-based NER methods, MProto represents each entity type with multipleprototypes to characterize the intra-class variance among entityrepresentations. To optimize the classifier, each token should be assigned anappropriate ground-truth prototype and we consider such token-prototypeassignment as an optimal transport (OT) problem. Furthermore, to mitigate thenoise from incomplete labeling, we propose a novel denoised optimal transport(DOT) algorithm. Specifically, we utilize the assignment result between Otherclass tokens and all prototypes to distinguish unlabeled entity tokens fromtrue negatives. Experiments on several DS-NER benchmarks demonstrate that ourMProto achieves state-of-the-art performance. The source code is now availableon Github.

MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition