Autoencoding Word Representations through Time for Semantic Change Detection

TL;DR

This paper introduces sequential models that track the evolution of word embeddings over time to improve the detection of semantic change, demonstrating that temporal modeling significantly enhances performance over static comparison methods.

Contribution

It proposes three variants of sequential models for semantic change detection, emphasizing the importance of temporal dynamics in word representation evolution.

Findings

Sequential models outperform static comparison methods.

Temporal modeling improves detection accuracy.

Experiments on synthetic and real data validate the approach.

Abstract

Semantic change detection concerns the task of identifying words whose meaning has changed over time. The current state-of-the-art detects the level of semantic change in a word by comparing its vector representation in two distinct time periods, without considering its evolution through time. In this work, we propose three variants of sequential models for detecting semantically shifted words, effectively accounting for the changes in the word representations over time, in a temporally sensitive manner. Through extensive experimentation under various settings with both synthetic and real data we showcase the importance of sequential modelling of word vectors through time for detecting the words whose semantics have changed the most. Finally, we take a step towards comparing different approaches in a quantitative manner, demonstrating that the temporal modelling of word representations yields a clear-cut advantage in performance.