This paper surveys the current state of the art in Natural Language Generation (NLG),
defined as the task of generating text or speech from non-linguistic input. A survey of NLG is …

Abstract Language allows us to efficiently communicate about the things in the world around
us. Seemingly simple words like this and that are a cornerstone of our capability to refer, as …

In this paper we introduce a new game to crowd-source natural language referring
expressions. By designing a two player game, we can both collect and verify referring …

Color adjectives tend to be used redundantly in referential communication. I propose that
redundant color adjectives (RCAs) are often intended to exploit a color contrast in the visual …

Speakers often overspecify their target descriptions and include more information than
necessary for unique identification of the target referent. In the current paper, we study the …

How do comprehenders reason about pragmatically ambiguous scalar terms like some in
complex syntactic contexts? In many pragmatic theories of conversational implicature, local …

A foundational assumption of human communication is that speakers should say as much as
necessary, but no more. Yet, people routinely produce redundant adjectives and their …

This study investigates to what extent the amount of variation in a visual scene causes
speakers to mention the attribute color in their definite target descriptions, focusing on …

We introduce a novel algorithm for generating referring expressions, informed by human
and computer vision and designed to refer to visible objects. Our method separates absolute …

When speakers describe objects with atypical properties, do they include these properties in
their referring expressions, even when that is not strictly required for unique referent …