Semantics and Deep Learning
Lasha Abzianidze, Lisa Bylinina, Denis Paperno
September 2024 

The survey 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 survey closes with suggestions on possible deeper interactions between theoretical semantics and language technology based on deep learning models.

Format:	[ pdf ]
Reference:	lingbuzz/007736 (please use that when you cite this article)
Published in:	Draft of a survey written for Cambridge Elements in Semantics
keywords:	semantics, deep learning, inference, compositionality, language and vision
previous versions:	v1 [December 2023]
Downloaded:	1003 times

 

[ edit this article | back to article list ]