# Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision

## TL;DR

This paper explores how models can learn the meanings of cardinals and quantifiers from visual scenes, showing that fuzzy similarity aids quantifier learning while explicit number info benefits cardinal learning.

## Contribution

It introduces two models tailored for learning the meanings of cardinals and quantifiers from visual data, highlighting the importance of different information types for each.

## Key findings

- Fuzzy similarity models effectively learn quantifiers.
- Number information improves cardinal learning.
- Different mechanisms are needed for cardinals and quantifiers.

## Abstract

People can refer to quantities in a visual scene by using either exact cardinals (e.g. one, two, three) or natural language quantifiers (e.g. few, most, all). In humans, these two processes underlie fairly different cognitive and neural mechanisms. Inspired by this evidence, the present study proposes two models for learning the objective meaning of cardinals and quantifiers from visual scenes containing multiple objects. We show that a model capitalizing on a 'fuzzy' measure of similarity is effective for learning quantifiers, whereas the learning of exact cardinals is better accomplished when information about number is provided.