AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity

arXiv · AI, language, vision and robotics · article · Oct 30, 2026 · UTC

While sentence embeddings are primarily designed for semantic generalization, their latent geometry implicitly encodes surface-level lexical properties, a relationship that remains poorly understood. Shallow pooling methods discard word order, while deep Transformer models obscure these lexical alignments behind computational complexity and uninterpretable spaces. We propose constructing sentence embeddings via the path signature of Word2Vec trajectories, leveraging the iterated integrals of rough path theory to create representations that explicitly capture sequential and lexical structure in

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-11-02T10:21:21.339Z. This is not the publication date.