Generating One-Anaphoric Expressions: Where Does the Decision Lie?

TL;DR

This paper explores the generation of one-anaphoric expressions in natural language systems, proposing a revised approach that enhances referring expression generation, demonstrated through a database interface application.

Contribution

It introduces a novel method for generating one-anaphoric expressions, revising existing assumptions in referring expression algorithms.

Findings

Improved generation of one-anaphoric expressions in NLG systems

Demonstrated effectiveness in a database interface context

Insights into broader implications for referring expression generation

Abstract

Most natural language generation systems embody mechanisms for choosing whether to subsequently refer to an already-introduced entity by means of a pronoun or a definite noun phrase. Relatively few systems, however, consider referring to entites by means of one-anaphoric expressions such as \lingform{the small green one}. This paper looks at what is involved in generating referring expressions of this type. Consideration of how to fit this capability into a standard algorithm for referring expression generation leads us to suggest a revision of some of the assumptions that underlie existing approaches. We demonstrate the usefulness of our approach to one-anaphora generation in the context of a simple database interface application, and make some observations about the impact of this approach on referring expression generation more generally.