Lexical Semantic Change Discovery

TL;DR

This paper shifts focus from detecting lexical semantic change to discovering new word senses over time, presenting a fine-tuned, automated framework for discovery and evaluation using German data.

Contribution

It introduces a novel approach for discovering lexical semantic change, moving beyond standard detection to sense discovery with an automated framework.

Findings

Both models successfully discover words with meaning change.

The framework is effective and nearly fully automated.

Models are fine-tuned on recent German data.

Abstract

While there is a large amount of research in the field of Lexical Semantic Change Detection, only few approaches go beyond a standard benchmark evaluation of existing models. In this paper, we propose a shift of focus from change detection to change discovery, i.e., discovering novel word senses over time from the full corpus vocabulary. By heavily fine-tuning a type-based and a token-based approach on recently published German data, we demonstrate that both models can successfully be applied to discover new words undergoing meaning change. Furthermore, we provide an almost fully automated framework for both evaluation and discovery.