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

Paper recorded by Signals 4 on 2026-10-30 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-30 on arXiv · recorded by Signals 4 on 2026-11-02

Category: cs.CL · 自然语言处理 · first seen 2026-11-02

Abstract

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

Read on arXiv →