id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_b5zqmaftfja27l2uav7i55veou	Felix Hill	Multi-Modal Models for Concrete and Abstract Concept Meaning	2014	12	.pdf	application/pdf	7510	610	53	Multi-Modal Models for Concrete and Abstract Concept Meaning Multi-modal models that learn semantic representations from both linguistic and perceptual input outperform language-only models a means of propagating perceptual information from concrete nouns to more abstract concepts that is more robust than previous approaches. models in these studies corresponds directly to concrete noun concepts, such as chocolate or cheeseburger, and the superiority of the multi-modal over We construct models that acquire semantic representations for four sets of concepts: concrete nouns, perceptual information to abstract nouns and concrete verbs, and is overall preferable to both linear regression and the method of Johns and Jones Figure 1: Boxplot of concreteness distributions for noun and verb concepts in the USF data, with selected example We create evaluation sets of abstract and concrete concepts, and introduce a complementary dichotomy between nouns and verbs, the two POS categories most fundamental to propositional meaning.	./cache/work_b5zqmaftfja27l2uav7i55veou.pdf	./txt/work_b5zqmaftfja27l2uav7i55veou.txt