Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches
This work addresses the problem of enabling AI systems to use context effectively for natural communication, but it is incremental as it primarily reviews and synthesizes existing research.
The paper surveys how context enriches meaning in language grounding for AI systems, analyzing existing tasks and modeling approaches, and provides recommendations for future task design to better incorporate pragmatic phenomena.
People rely heavily on context to enrich meaning beyond what is literally said, enabling concise but effective communication. To interact successfully and naturally with people, user-facing artificial intelligence systems will require similar skills in pragmatics: relying on various types of context -- from shared linguistic goals and conventions, to the visual and embodied world -- to use language effectively. We survey existing grounded settings and pragmatic modeling approaches and analyze how the task goals, environmental contexts, and communicative affordances in each work enrich linguistic meaning. We present recommendations for future grounded task design to naturally elicit pragmatic phenomena, and suggest directions that focus on a broader range of communicative contexts and affordances.