Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices
This work addresses the need for more efficient and detailed semantic shift analysis in computational linguistics, though it appears incremental as it builds on existing embedding methods.
The paper tackles the problem of analyzing detailed semantic shifts over multiple time periods by proposing a framework that uses diachronic word similarity matrices, enabling deeper analysis and unsupervised categorization of words with similar shift behaviors.
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.