Generating Quantified Descriptions of Abstract Visual Scenes

Abstract

Quantified expressions have always taken up a central position in formal theories of meaning and language use. Yet quantified expressions have so far attracted far less attention from the Natural Language Generation community than, for example, referring expressions. In an attempt to start redressing the balance, we investigate a recently developed corpus in which quantified expressions play a crucial role; the corpus is the result of a carefully controlled elicitation experiment, in which human participants were asked to describe visually presented scenes. Informed by an analysis of this corpus, we propose algorithms that produce computer-generated descriptions of a wider class of visual scenes, and we evaluate the descriptions generated by these algorithms in terms of their correctness, completeness, and human-likeness. We discuss what this exercise can teach us about the nature of quantification and about the challenges posed by the generation of quantified expressions.

QTUNA: A Corpus for Understanding How Speakers Use Quantification

“…(For example, the corpus can help us understand which quantifiers and QE patterns are most frequently used, and how elaborate a description needs to be -for example, when should the generator stop adding further QEs, be-cause it has provided enough information already, whether or not the scene has been described completely.) Examples of such a generation algorithm, based on the corpus of the present paper, can be found in Chen et al (2019).…”