Long-Range Dependence in Word Time Series: The Cosine Correlation of Embeddings

We analyze long-range dependence (LRD) for word time series, understood as a slower than exponential decay of the two-point Shannon mutual information. We achieve this by examining the decay of the cosine correlation, a proxy object defined in terms of the cosine similarity between word2vec embeddin...

Full description

Saved in:
Bibliographic Details
Main Authors: Paweł Wieczyński, Łukasz Dębowski
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/6/613
Tags: Add Tag
No Tags, Be the first to tag this record!