Systematicity, compositionality and transitivity of deep NLP models: A metamorphic testing perspective,

· 2022 · Findings of the Association for Computational Linguistics: ACL 2022 · DOI 10.18653/v1/2022.findings-acl.185

1 Pith paper cite this work, alongside 5 external citations. Polarity classification is still indexing.

1 Pith paper citing it

5 external citations · OpenAlex

open at publisher browse 1 citing papers

representative citing papers

cs.SE · 2026-07-31 · conditional · novelty 5.0

Version-to-version metamorphic testing can surface NLP classifier regressions — 16 found, 11 release-blocking — that aggregate accuracy metrics mask.

Showing 1 of 1 citing paper.

Alteron: A Tool for Behavioral Regression Testing Across NLP Classifier Versions cs.SE · 2026-07-31 · conditional · none · ref 15
Version-to-version metamorphic testing can surface NLP classifier regressions — 16 found, 11 release-blocking — that aggregate accuracy metrics mask.