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

This technical report describes a new prototype architecture designed tointegrate top-down and bottom-up analysis of non-standard linguistic input,where a semantic model of the context of an utterance is used to guide theanalysis of the non-standard surface forms, including their automatednormalization in context. While the architecture is generally applicable, as aconcrete use case of the architecture we target the generation ofsemantically-informed target hypotheses for answers written by German learnersin response to reading comprehension questions, where the reading context andpossible target answers are given.  The architecture integrates existing NLP components to produce candidateanalyses on eight levels of linguistic modeling, all of which are broken downinto atomic statements and connected into a large graphical model usingProbabilistic Soft Logic (PSL) as a framework. Maximum a posteriori inferenceon the resulting graphical model then assigns a belief distribution tocandidate target hypotheses. The current version of the architecture builds onUniversal Dependencies (UD) as its representation formalism on the form leveland on Abstract Meaning Representations (AMRs) to represent semantic analysesof learner answers and the context information provided by the target answers.These general choices will make it comparatively straightforward to apply thearchitecture to other tasks and other languages.

Exploring Probabilistic Soft Logic as a framework for integrating top-down and bottom-up processing of language in a task context