Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision
This addresses how AI systems can interpret human-like quantity references from vision, but it is incremental as it builds on known cognitive mechanisms.
The study tackled the problem of learning the meaning of cardinals and quantifiers from visual scenes by proposing two models, showing that a fuzzy similarity measure is effective for quantifiers while number information is better for cardinals.
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.