Visualitza Congressos (Departament de Traducció i Ciències del Llenguatge) per autoria "Lapata, Mirella"

Ara mostrant els elements 1-2 de 2

Grounded models of semantic representation

Silberer, Carina; Lapata, Mirella (ACL (Association for Computational Linguistics), 2012)

A popular tradition of studying semantic representation has been driven by the assumption that word meaning can be learned from the linguistic environment, despite ample evidence suggesting that language is grounded in ...
Models of semantic representation with visual attribute

Silberer, Carina; Ferrari, Vittorio; Lapata, Mirella (ACL (Association for Computational Linguistics), 2013)

We consider the problem of grounding the meaning of words in the physical world and focus on the visual modality which we represent by visual attributes. We create a new large-scale taxonomy of visual attributes covering ...