Grounding 'Grounding' in NLP

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.

arXiv comment24 pages

References in corpus (11)

• Representations of language in a model of visually grounded speech signal
• Visually Grounded Neural Syntax Acquisition
• BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
• Explaining Question Answering Models through Text Generation
• Learning to summarize from human feedback
• Text to 3D Scene Generation with Rich Lexical Grounding
• ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)
• "My Way of Telling a Story": Persona based Grounded Story Generation
• Induction and Reference of Entities in a Visual Story
• A recipe for annotating grounded clarifications
• Denoising Large-Scale Image Captioning from Alt-text Data using Content Selection Models