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

Unsupervised relation extraction (URE) aims to extract relations betweennamed entities from raw text without requiring manual annotations orpre-existing knowledge bases. In recent studies of URE, researchers put anotable emphasis on contrastive learning strategies for acquiring relationrepresentations. However, these studies often overlook two important aspects:the inclusion of diverse positive pairs for contrastive learning and theexploration of appropriate loss functions. In this paper, we propose AugUREwith both within-sentence pairs augmentation and augmentation throughcross-sentence pairs extraction to increase the diversity of positive pairs andstrengthen the discriminative power of contrastive learning. We also identifythe limitation of noise-contrastive estimation (NCE) loss for relationrepresentation learning and propose to apply margin loss for sentence pairs.Experiments on NYT-FB and TACRED datasets demonstrate that the proposedrelation representation learning and a simple K-Means clustering achievesstate-of-the-art performance.

Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs