Toward Givenness Hierarchy Theoretic Natural Language Generation

TL;DR

This paper explores how the Givenness Hierarchy theory can be adapted for natural language generation in robots to improve their ability to produce contextually appropriate anaphoric references during dialogue.

Contribution

It proposes a novel approach to applying GH theory specifically for robot anaphora generation, differing from previous understanding-focused methods.

Findings

Proposes a new GH-based framework for robot anaphora generation

Highlights differences in applying GH for generation versus understanding

Lays groundwork for more natural human-robot dialogue interactions

Abstract

Language-capable interactive robots participating in dialogues with human interlocutors must be able to naturally and efficiently communicate about the entities in their environment. A key aspect of such communication is the use of anaphoric language. The linguistic theory of the Givenness Hierarchy(GH) suggests that humans use anaphora based on the cognitive statuses their referents have in the minds of their interlocutors. In previous work, researchers presented GH-theoretic approaches to robot anaphora understanding. In this paper we describe how the GH might need to be used quite differently to facilitate robot anaphora generation.