Building a shared world: mapping distributional to model-theoretic semantic spaces

Abstract

In this paper, we introduce an approach to automatically map a standard distributional semantic space onto a set-theoretic model. We predict that there is a functional relationship between distributional information and vectorial concept representations in which dimensions are predicates and weights are generalised quantifiers. In order to test our prediction, we learn a model of such relationship over a publicly available dataset of feature norms annotated with natural language quantifiers. Our initial experimental results show that, at least for domain-specific data, we can indeed map between formalisms, and generate high-quality vector representations which encapsulate set overlap information. We further investigate the generation of natural language quantifiers from such vectors.

Instances and concepts in distributional space

“…An extremely interesting (and challenging) extension is to tackle "anonymous" entities for which standard distributional techniques do not work (my neighbor, the bird we saw this morning), in the spirit of Herbelot and Vecchi (2015) and Boleda et al (2017).…”

What do you know about an alligator when you know the company it keeps?

“…There is some empirical evidence that distributional data can be used for inferring properties in Johns & Jones 2012, Fȃgȃrȃşan, Vecchi & Clark 2015, Gupta et al 2015, and Herbelot & Vecchi 2015. They test whether distributional vectors can be used to predict a word's properties (where, as above, I use the term "properties of a word" to mean properties that apply to all entities in the word's extension).…”

“…Finally, there is a need for more research on distributional models for property inference, to develop efficient models beyond the initial approaches proposed by Johns & Jones (2012), Fȃgȃrȃşan, Vecchi & Clark (2015), Herbelot & Vecchi (2015) and Gupta et al (2015) and to see what kinds of properties can be reliably learned and whether verb properties can be learned as well as noun properties.…”

“Look, some Green Circles!”: Learning to Quantify from Images

“…no, some, all). Quantifiers are an emerging field of research in distributional semantics (Grefenstette, 2013;Herbelot and Vecchi, 2015) and, so far, haven't been studied in relation with visual data and grounding. We make a first step in this direction by asking whether the meaning of quantifier words can be learnt by observing their use in the presence of visual information.…”