Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs

TL;DR

This paper explores embedding digital dictionaries into AMR graphs using large language models, applying confluent reductions to analyze their properties and address the symbol grounding problem.

Contribution

It introduces a novel method of embedding dictionaries into AMR graphs and applies confluent reductions to study their properties related to symbol grounding.

Findings

Reduced AMR graphs preserve semantic information

Transformations maintain the circuit space of graphs

Insights into the symbol grounding problem

Abstract

Abstract meaning representation (AMR) is a semantic formalism used to represent the meaning of sentences as directed acyclic graphs. In this paper, we describe how real digital dictionaries can be embedded into AMR directed graphs (digraphs), using state-of-the-art pre-trained large language models. Then, we reduce those graphs in a confluent manner, i.e. with transformations that preserve their circuit space. Finally, the properties of these reduces digraphs are analyzed and discussed in relation to the symbol grounding problem.