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

Abstract excerpt

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 do it by examining the decay of the cosine correlation, a proxy object defined in terms of the cosine similarity between word2vec embeddings of two words, computed by an analogy to the Pearson correlation. By the Pinsker inequality, the squared cosine correlatio...

Topics

Open a Topic to create a Post that cites this publication.

• Algorithms
• Bayes Theorem
• Computational Biology
• Lung Neoplasms
• Mutation
• Phenotype
• Proto-Oncogene Proteins p21(ras)
• Tumor Suppressor Protein p53

Identifiers and source

Literature Corpus work

361a2859-41c7-50f7-be1e-352403577744

DOI

10.20944/preprints202505.1176.v1