Grounding from an AI and Cognitive Science Lens

Goonmeet Bajaj,Valerie L. Shalin,Srinivasan Parthasarathy,Amit Sheth

IEEE Intelligent Systems（2024）

Ohio State Univ | Wright State Univ | Univ South Carolina

Cited 0|Views45

Abstract

Grounding is a challenging problem, requiring a formal definition anddifferent levels of abstraction. This article explores grounding from bothcognitive science and machine learning perspectives. It identifies thesubtleties of grounding, its significance for collaborative agents, andsimilarities and differences in grounding approaches in both communities. Thearticle examines the potential of neuro-symbolic approaches tailored forgrounding tasks, showcasing how they can more comprehensively addressgrounding. Finally, we discuss areas for further exploration and development ingrounding.

Translated text

Key words

Grounding,Collaboration,Machine learning,Cognitive science,Task analysis,Intelligent systems,Artificial intelligence,Neural engineering,Symbols

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Try using models to generate summary,it takes about 60s

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper