Semantics and Deep Learning

This Element covers the interaction of two research areas: linguistic semantics and deep learning.

Lasha Abzianidze (Author), Lisa Bylinina (Author), Denis Paperno (Author)

9781009542395, Cambridge University Press

Hardback, published 16 January 2025

90 pages
23.5 x 16 x 0.9 cm, 0.284 kg

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.

1. Introduction
2. Textual Inference
3. Compositionality
4. Grounding: Language and Vision
5. Conclusions, open problems and further directions
References.

Subject Areas: Semantics, discourse analysis, etc [CFG]