Probing Natural Language Inference Models through Semantic Fragments
national conference on artificial intelligence, 2020.
Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena are involved in natural language inference (N...More
PPT (Upload PPT)