Semantics and Deep Learning

Abstract

This Element covers the interaction of two research areas: linguistic semantics and deep learning. It focuses on three phenomena central to natural language interpretation: reasoning and inference; compositionality; extralinguistic grounding. Representation of these phenomena in recent neural models is discussed, along with the quality of these representations and ways to evaluate them (datasets, tests, measures). The Element closes with suggestions on possible deeper interactions between theoretical semantics and language technology based on deep learning models.