Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yamagiwa, Hiroaki, Oyama, Momose, Shimodaira, Hidetoshi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913615008759808
author Yamagiwa, Hiroaki
Oyama, Momose
Shimodaira, Hidetoshi
author_facet Yamagiwa, Hiroaki
Oyama, Momose
Shimodaira, Hidetoshi
contents Cosine similarity is widely used to measure the similarity between two embeddings, while interpretations based on angle and correlation coefficient are common. In this study, we focus on the interpretable axes of embeddings transformed by Independent Component Analysis (ICA), and propose a novel interpretation of cosine similarity as the sum of semantic similarities over axes. The normalized ICA-transformed embeddings exhibit sparsity, enhancing the interpretability of each axis, and the semantic similarity defined by the product of the components represents the shared meaning between the two embeddings along each axis. The effectiveness of this approach is demonstrated through intuitive numerical examples and thorough numerical experiments. By deriving the probability distributions that govern each component and the product of components, we propose a method for selecting statistically significant axes.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10984
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings
Yamagiwa, Hiroaki
Oyama, Momose
Shimodaira, Hidetoshi
Computation and Language
Cosine similarity is widely used to measure the similarity between two embeddings, while interpretations based on angle and correlation coefficient are common. In this study, we focus on the interpretable axes of embeddings transformed by Independent Component Analysis (ICA), and propose a novel interpretation of cosine similarity as the sum of semantic similarities over axes. The normalized ICA-transformed embeddings exhibit sparsity, enhancing the interpretability of each axis, and the semantic similarity defined by the product of the components represents the shared meaning between the two embeddings along each axis. The effectiveness of this approach is demonstrated through intuitive numerical examples and thorough numerical experiments. By deriving the probability distributions that govern each component and the product of components, we propose a method for selecting statistically significant axes.
title Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings
topic Computation and Language
url https://arxiv.org/abs/2406.10984