The Geometry of Meaning: Perfect Spacetime Representations of Hierarchical Structures
This work addresses the representation of hierarchical meaning in AI and linguistics by proposing a geometric approach, but it is incremental as it builds on existing embedding methods with a novel spacetime twist.
The authors tackled the problem of embedding hierarchical structures in a geometric space by developing a fast algorithm that embeds them in three-dimensional Minkowski spacetime, achieving perfect embeddings for WordNet subsets with exact reproduction of ground-truth hierarchies.
We show that there is a fast algorithm that embeds hierarchical structures in three-dimensional Minkowski spacetime. The correlation of data ends up purely encoded in the causal structure. Our model relies solely on oriented token pairs -- local hierarchical signals -- with no access to global symbolic structure. We apply our method to the corpus of \textit{WordNet}. We provide a perfect embedding of the mammal sub-tree including ambiguities (more than one hierarchy per node) in such a way that the hierarchical structures get completely codified in the geometry and exactly reproduce the ground-truth. We extend this to a perfect embedding of the maximal unambiguous subset of the \textit{WordNet} with 82{,}115 noun tokens and a single hierarchy per token. We introduce a novel retrieval mechanism in which causality, not distance, governs hierarchical access. Our results seem to indicate that all discrete data has a perfect geometrical representation that is three-dimensional. The resulting embeddings are nearly conformally invariant, indicating deep connections with general relativity and field theory. These results suggest that concepts, categories, and their interrelations, namely hierarchical meaning itself, is geometric.