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

Distant supervision makes it possible to automatically label bags ofsentences for relation extraction by leveraging knowledge bases, but suffersfrom the sparse and noisy bag issues. Additional information sources areurgently needed to supplement the training data and overcome these issues. Inthis paper, we introduce two widely-existing sources in knowledge bases, namelyentity descriptions, and multi-grained entity types to enrich the distantlysupervised data. We see information sources as multiple views and fusing themto construct an intact space with sufficient information. An end-to-endmulti-view learning framework is proposed for relation extraction via IntactSpace Representation Learning (InSRL), and the representations of single viewsare jointly learned simultaneously. Moreover, inner-view and cross-viewattention mechanisms are used to highlight important information on differentlevels on an entity-pair basis. The experimental results on a popular benchmarkdataset demonstrate the necessity of additional information sources and theeffectiveness of our framework. We will release the implementation of our modeland dataset with multiple information sources after the anonymized reviewphase.

InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction