Grounding 'Grounding' in NLP

TL;DR

This paper examines the concept of grounding in NLP, comparing it with Cognitive Science definitions, analyzing current research trends, and proposing ways to develop more comprehensive grounding tasks.

Contribution

It clarifies the differences between NLP and Cognitive Science notions of grounding and suggests new directions for creating tasks that better capture the full scope of grounding.

Findings

Identifies missing aspects of grounding in NLP tasks: coordination, purviews, constraints.

Analyzes trends in datasets, domains, and tasks in recent NLP research.

Proposes methods to develop new or repurpose existing tasks for better grounding.

Abstract

The NLP community has seen substantial recent interest in grounding to facilitate interaction between language technologies and the world. However, as a community, we use the term broadly to reference any linking of text to data or non-textual modality. In contrast, Cognitive Science more formally defines "grounding" as the process of establishing what mutual information is required for successful communication between two interlocutors -- a definition which might implicitly capture the NLP usage but differs in intent and scope. We investigate the gap between these definitions and seek answers to the following questions: (1) What aspects of grounding are missing from NLP tasks? Here we present the dimensions of coordination, purviews and constraints. (2) How is the term "grounding" used in the current research? We study the trends in datasets, domains, and tasks introduced in recent NLP conferences. And finally, (3) How to advance our current definition to bridge the gap with Cognitive Science? We present ways to both create new tasks or repurpose existing ones to make advancements towards achieving a more complete sense of grounding.