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

Metamorphic testing has recently been used to check the safety of neural NLPmodels. Its main advantage is that it does not rely on a ground truth togenerate test cases. However, existing studies are mostly concerned withrobustness-like metamorphic relations, limiting the scope of linguisticproperties they can test. We propose three new classes of metamorphicrelations, which address the properties of systematicity, compositionality andtransitivity. Unlike robustness, our relations are defined over multiple sourceinputs, thus increasing the number of test cases that we can produce by apolynomial factor. With them, we test the internal consistency ofstate-of-the-art NLP models, and show that they do not always behave accordingto their expected linguistic properties. Lastly, we introduce a novel graphicalnotation that efficiently summarises the inner structure of metamorphicrelations.

Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective