The Pragmatics of Indirect Commands in Collaborative Discourse

TL;DR

This paper explores how indirect commands, especially locatives, function in collaborative tasks to elicit actions, emphasizing the importance of pragmatic reasoning for natural human-AI interactions.

Contribution

It introduces a framework for understanding and modeling indirect commands in collaborative discourse, focusing on locatives and their contextual interpretation.

Findings

Models with domain-specific grounding effectively interpret indirect commands.

Locative utterances can serve as indirect commands in collaborative settings.

Pragmatic reasoning enhances natural language interaction robustness.

Abstract

Today's artificial assistants are typically prompted to perform tasks through direct, imperative commands such as \emph{Set a timer} or \emph{Pick up the box}. However, to progress toward more natural exchanges between humans and these assistants, it is important to understand the way non-imperative utterances can indirectly elicit action of an addressee. In this paper, we investigate command types in the setting of a grounded, collaborative game. We focus on a less understood family of utterances for eliciting agent action, locatives like \emph{The chair is in the other room}, and demonstrate how these utterances indirectly command in specific game state contexts. Our work shows that models with domain-specific grounding can effectively realize the pragmatic reasoning that is necessary for more robust natural language interaction.