Saved in:
Bibliographic Details
Main Authors: Goulet, Nicolas, Massé, Alexandre Blondin, Abdendi, Moussa
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.11068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916901195612160
author Goulet, Nicolas
Massé, Alexandre Blondin
Abdendi, Moussa
author_facet Goulet, Nicolas
Massé, Alexandre Blondin
Abdendi, Moussa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs
Goulet, Nicolas
Massé, Alexandre Blondin
Abdendi, Moussa
Computation and Language
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.
title Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs
topic Computation and Language
url https://arxiv.org/abs/2508.11068