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

Previous entity disambiguation (ED) methods adopt a discriminative paradigm,where prediction is made based on matching scores between mention context andcandidate entities using length-limited encoders. However, these methods oftenstruggle to capture explicit discourse-level dependencies, resulting inincoherent predictions at the abstract level (e.g. topic or category). Wepropose CoherentED, an ED system equipped with novel designs aimed at enhancingthe coherence of entity predictions. Our method first introduces anunsupervised variational autoencoder (VAE) to extract latent topic vectors ofcontext sentences. This approach not only allows the encoder to handle longerdocuments more effectively, conserves valuable input space, but also keeps atopic-level coherence. Additionally, we incorporate an external categorymemory, enabling the system to retrieve relevant categories for undecidedmentions. By employing step-by-step entity decisions, this design facilitatesthe modeling of entity-entity interactions, thereby maintaining maximumcoherence at the category level. We achieve new state-of-the-art results onpopular ED benchmarks, with an average improvement of 1.3 F1 points. Our modeldemonstrates particularly outstanding performance on challenging long-textscenarios.

Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency