Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices

TL;DR

This paper introduces a lightweight framework using diachronic word similarity matrices to analyze continuous semantic shifts over multiple time periods, enabling detailed and unsupervised categorization of semantic change patterns.

Contribution

The authors propose a novel, efficient method leveraging similarity matrices to study semantic shifts across multiple periods, overcoming limitations of previous approaches.

Findings

Effective analysis of semantic shifts over multiple periods.

Unsupervised categorization of words with similar semantic change patterns.

Lightweight computation suitable for large-scale diachronic studies.

Abstract

The meanings and relationships of words shift over time. This phenomenon is referred to as semantic shift. Research focused on understanding how semantic shifts occur over multiple time periods is essential for gaining a detailed understanding of semantic shifts. However, detecting change points only between adjacent time periods is insufficient for analyzing detailed semantic shifts, and using BERT-based methods to examine word sense proportions incurs a high computational cost. To address those issues, we propose a simple yet intuitive framework for how semantic shifts occur over multiple time periods by leveraging a similarity matrix between the embeddings of the same word through time. We compute a diachronic word similarity matrix using fast and lightweight word embeddings across arbitrary time periods, making it deeper to analyze continuous semantic shifts. Additionally, by clustering the similarity matrices for different words, we can categorize words that exhibit similar behavior of semantic shift in an unsupervised manner.