Approaching the Source of Symbol Grounding with Confluent Reductions of Abstract Meaning Representation Directed Graphs
This work addresses the symbol grounding problem in AI and linguistics, but it appears incremental as it builds on existing AMR and LLM methods without claiming major breakthroughs.
The paper tackled the symbol grounding problem by embedding real digital dictionaries into Abstract Meaning Representation directed graphs using pre-trained large language models and reducing them confluently, analyzing the properties of the reduced graphs to approach the source of symbol grounding.
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.