ReFRAME or Remain: Unsupervised Lexical Semantic Change Detection with Frame Semantics

TL;DR

This paper introduces a frame semantics-based approach for lexical semantic change detection, offering interpretability and competitive performance compared to neural embedding methods.

Contribution

It presents a novel, interpretable method for semantic change detection that outperforms many existing distributional models.

Findings

Frame semantics approach is effective for detecting semantic change.

The method can outperform many neural embedding-based models.

Predictions are both plausible and highly interpretable.

Abstract

The majority of contemporary computational methods for lexical semantic change (LSC) detection are based on neural embedding distributional representations. Although these models perform well on LSC benchmarks, their results are often difficult to interpret. We explore an alternative approach that relies solely on frame semantics. We show that this method is effective for detecting semantic change and can even outperform many distributional semantic models. Finally, we present a detailed quantitative and qualitative analysis of its predictions, demonstrating that they are both plausible and highly interpretable