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

Open-world Relation Extraction (OpenRE) has recently garnered significantattention. However, existing approaches tend to oversimplify the problem byassuming that all unlabeled texts belong to novel classes, thereby limiting thepracticality of these methods. We argue that the OpenRE setting should be morealigned with the characteristics of real-world data. Specifically, we proposetwo key improvements: (a) unlabeled data should encompass known and novelclasses, including hard-negative instances; and (b) the set of novel classesshould represent long-tail relation types. Furthermore, we observe that popularrelations such as titles and locations can often be implicitly inferred throughspecific patterns, while long-tail relations tend to be explicitly expressed insentences. Motivated by these insights, we present a novel method called KNoRD(Known and Novel Relation Discovery), which effectively classifies explicitlyand implicitly expressed relations from known and novel classes withinunlabeled data. Experimental evaluations on several Open-world RE benchmarksdemonstrate that KNoRD consistently outperforms other existing methods,achieving significant performance gains.

Open-world Semi-supervised Generalized Relation Discovery Aligned in a Real-world Setting