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

Nicolas Goulet, Alexandre Blondin Massé, Moussa Abdendi
8/14/2025
cs.CL

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM

83% match1 repo12024

SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation

82% match2025

Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding

79% match1 repo12025

Neurosymbolic Graph Enrichment for Grounded World Models

78% match2024

From Anchors to Answers: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models

76% match2024

Applying Text Embedding Models for Efficient Analysis in Labeled Property Graphs

76% match2025

Cite this paper

@article{goulet2025approaching,
  title  = {Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs},
  author = {Nicolas Goulet and Alexandre Blondin Massé and Moussa Abdendi},
  year   = {2025},
  eprint = {2508.11068},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.11068v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.11068.svg)](https://codeofpaper.com/paper/2508.11068)

Discussion