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

Text-rich heterogeneous information networks (text-rich HINs) are ubiquitousin real-world applications. Hypernymy, also known as is-a relation orsubclass-of relation, lays in the core of many knowledge graphs and benefitsmany downstream applications. Existing methods of hypernymy discovery eitherleverage textual patterns to extract explicitly mentioned hypernym-hyponympairs, or learn a distributional representation for each term of interest basedits context. These approaches rely on statistical signals from the textualcorpus, and their effectiveness would therefore be hindered when the signalsfrom the corpus are not sufficient for all terms of interest. In this work, wepropose to discover hypernymy in text-rich HINs, which can introduce additionalhigh-quality signals. We develop a new framework, named HyperMine, thatexploits multi-granular contexts and combines signals from both text andnetwork without human labeled data. HyperMine extends the definition of contextto the scenario of text-rich HIN. For example, we can define typed nodes andcommunities as contexts. These contexts encode signals of differentgranularities and we feed them into a hypernymy inference model. HyperMinelearns this model using weak supervision acquired based on high-precisiontextual patterns. Extensive experiments on two large real-world datasetsdemonstrate the effectiveness of HyperMine and the utility of modeling contextgranularity. We further show a case study that a high-quality taxonomy can begenerated solely based on the hypernymy discovered by HyperMine.

Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity