Unravelling Interlanguage Facts via Explainable Machine Learning

no code implementations • 2 Aug 2022 • Barbara Berti, Andrea Esuli, Fabrizio Sebastiani

We focus on a different facet of the NLI task, i. e., that of analysing the internals of an NLI classifier trained by an \emph{explainable} machine learning algorithm, in order to obtain explanations of its classification decisions, with the ultimate goal of gaining insight into which linguistic phenomena ``give a speaker's native language away''.

BIG-bench Machine Learning Native Language Identification