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

Despite the recent success of deep neural networks in natural languageprocessing, the extent to which they can demonstrate human-like generalizationcapacities for natural language understanding remains unclear. We explore thisissue in the domain of natural language inference (NLI), focusing on thetransitivity of inference relations, a fundamental property for systematicallydrawing inferences. A model capturing transitivity can compose basic inferencepatterns and draw new inferences. We introduce an analysis method usingsynthetic and naturalistic NLI datasets involving clause-embedding verbs toevaluate whether models can perform transitivity inferences composed ofveridical inferences and arbitrary inference types. We find that current NLImodels do not perform consistently well on transitivity inference tasks,suggesting that they lack the generalization capacity for drawing compositeinferences from provided training examples. The data and code for our analysisare publicly available at https://github.com/verypluming/transitivity.

Exploring Transitivity in Neural NLI Models through Veridicality