Trabalho em anais de eventoOpen Access
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective
MANINO, E.; ROZANOVA, J.; CARVALHO, D.; FREITAS, A.; CORDEIRO, L. C
Resumo
Resumo
Metamorphic testing has recently been used to check the safety of neural NLP models.Its main advantage is that it does not rely on a ground truth to generate test cases.However, existing studies are mostly concerned with robustness-like metamorphic relations, limiting the scope of linguistic properties they can test.We propose three new classes of metamorphic relations, which address the properties of systematicity, compositionality and transitivity.Unlike robustness, our relations are defined over multiple source inputs, thus increasing the number of test cases that we can produce by a polynomial factor.With them, we test the internal consistency of state-of-theart NLP models, and show that they do not always behave according to their expected linguistic properties.Lastly, we introduce a novel graphical notation that efficiently summarises the inner structure of metamorphic relations.
palavras-chave
Palavras-chave
metamorphic testingsystematicitycompositionalitytransitivitymetamorphic relationsmodel safety
Status
Published
links
Links e arquivos
Trabalho em anais de evento