Pragmatic and Logical Inferences in NLI Systems: The Case of Conjunction Buttressing

Paolo Pedinotti, Emmanuele Chersoni, Enrico Santus, Alessandro Lenci
2022 Proceedings of the Second Workshop on Understanding Implicit and Underspecified Language   unpublished
An intelligent system is expected to perform reasonable inferences, accounting for both the literal meaning of a word and the meanings a word can acquire in different contexts. A specific kind of inference concerns the connective and, which in some cases gives rise to a temporal succession or causal interpretation in contrast with the logic, commutative one (Levinson, 2000) . In this work, we investigate the phenomenon by creating a new dataset for evaluating the interpretation of and by NLI
more » ... tems, which we use to test three Transformer-based models. Our results show that all systems generalize patterns that are consistent with both the logical and the pragmatic interpretation, perform inferences that are inconsistent with each other, and show clear divergences with both theoretical accounts and humans' behavior.
doi:10.18653/v1/2022.unimplicit-1.2 fatcat:paecwkwttjch3piunyx4eon6lu