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

An emerging line of research in Explainable NLP is the creation of datasetsenriched with human-annotated explanations and rationales, used to build andevaluate models with step-wise inference and explanation generationcapabilities. While human-annotated explanations are used as ground-truth forthe inference, there is a lack of systematic assessment of their consistencyand rigour. In an attempt to provide a critical quality assessment ofExplanation Gold Standards (XGSs) for NLI, we propose a systematic annotationmethodology, named Explanation Entailment Verification (EEV), to quantify thelogical validity of human-annotated explanations. The application of EEV onthree mainstream datasets reveals the surprising conclusion that a majority ofthe explanations, while appearing coherent on the surface, represent logicallyinvalid arguments, ranging from being incomplete to containing clearlyidentifiable logical errors. This conclusion confirms that the inferentialproperties of explanations are still poorly formalised and understood, and thatadditional work on this line of research is necessary to improve the wayExplanation Gold Standards are constructed.

Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards