Skip to content

Introduction

Semantic shift is a phenomenon that occurs naturally in all languages as the meaning of words can change over time due to various factors such as cultural shifts, technological advancements, and language contact. Understanding the semantic evolution of words is crucial for fields such as historical linguistics, cultural studies, and language technology. Etymology, the study of the origin and history of words, plays a pivotal role in tracing the development of words from their earliest known use to their current usage, and exam- ining the ways in which their meanings and forms have changed over time. The study of semantic shift is also vital for improving language technology applications such as search engines, content recommendation systems, and machine translation. For instance, track- ing semantic change can help search engines and content recommendation systems to provide more relevant and accurate results to users, and it can also improve the accuracy of machine translation systems. Traditional methods for tracking semantic shift involve manual annotation of texts and comparison of word usages across different time periods, which can be time-consuming and labor-intensive. However, recent advancements in natural language processing have led to the development of diachronic word embeddings, which offer a more efficient and au- tomated approach to tracking semantic shift. This study aims to explore the effectiveness of diachronic embeddings for semantic shift tracking.