# Learning dynamic word embeddings with drift regularisation

## TL;DR

This paper introduces a method for learning dynamic word embeddings that capture semantic changes over time, using drift regularization to improve the modeling of diachronic language evolution across English and French corpora.

## Contribution

It presents an extension of the Dynamic Bernoulli Embeddings model with drift regularization for better diachronic analysis of word meaning changes.

## Key findings

- Effective modeling of word meaning evolution over time.
- Cross-lingual analysis of language change.
- Demonstrated on English and French news corpora.

## Abstract

Word usage, meaning and connotation change throughout time. Diachronic word embeddings are used to grasp these changes in an unsupervised way. In this paper, we use variants of the Dynamic Bernoulli Embeddings model to learn dynamic word embeddings, in order to identify notable properties of the model. The comparison is made on the New York Times Annotated Corpus in English and a set of articles from the French newspaper Le Monde covering the same period. This allows us to define a pipeline to analyse the evolution of words use across two languages.