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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Many state-of-the-art natural language understanding (NLU) models are basedon pretrained neural language models. These models often make inferences usinginformation from multiple sources. An important class of such inferences arethose that require both background knowledge, presumably contained in a model'spretrained parameters, and instance-specific information that is supplied atinference time. However, the integration and reasoning abilities of NLU modelsin the presence of multiple knowledge sources have been largely understudied.In this work, we propose a test suite of coreference resolution subtasks thatrequire reasoning over multiple facts. These subtasks differ in terms of whichknowledge sources contain the relevant facts. We also introduce subtasks whereknowledge is present only at inference time using fictional knowledge. Weevaluate state-of-the-art coreference resolution models on our dataset. Ourresults indicate that several models struggle to reason on-the-fly overknowledge observed both at pretrain time and at inference time. However, withtask-specific training, a subset of models demonstrates the ability tointegrate certain knowledge types from multiple sources. Still, even the bestperforming models seem to have difficulties with reliably integrating knowledgepresented only at inference time.

The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems