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

Document-level relation extraction (RE) aims to identify relations betweenentities across multiple sentences. Most previous methods focused ondocument-level RE under full supervision. However, in real-world scenario, itis expensive and difficult to completely label all relations in a documentbecause the number of entity pairs in document-level RE grows quadraticallywith the number of entities. To solve the common incomplete labeling problem,we propose a unified positive-unlabeled learning framework - shift and squaredranking loss positive-unlabeled (SSR-PU) learning. We use positive-unlabeled(PU) learning on document-level RE for the first time. Considering that labeleddata of a dataset may lead to prior shift of unlabeled data, we introduce a PUlearning under prior shift of training data. Also, using none-class score as anadaptive threshold, we propose squared ranking loss and prove its Bayesianconsistency with multi-label ranking metrics. Extensive experiments demonstratethat our method achieves an improvement of about 14 F1 points relative to theprevious baseline with incomplete labeling. In addition, it outperformsprevious state-of-the-art results under both fully supervised and extremelyunlabeled settings as well.

A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling