Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts

TL;DR

This paper introduces a multilingual domain adaptation framework called Mixture of Temporal Experts (MoTE) that models and adapts to temporal shifts in data distributions across different languages, improving classification robustness over time.

Contribution

It proposes MoTE, a novel framework that leverages semantic and distributional shifts to adapt classifiers to temporal changes in multilingual data.

Findings

Classification performance varies over time across languages.

MoTE enhances classifier generalizability over temporal shifts.

Temporal effects are significant in multilingual classification tasks.

Abstract

Time is implicitly embedded in classification process: classifiers are usually built on existing data while to be applied on future data whose distributions (e.g., label and token) may change. However, existing state-of-the-art classification models merely consider the temporal variations and primarily focus on English corpora, which leaves temporal studies less explored, let alone under multilingual settings. In this study, we fill the gap by treating time as domains (e.g., 2024 vs. 2025), examining temporal effects, and developing a domain adaptation framework to generalize classifiers over time on multiple languages. Our framework proposes Mixture of Temporal Experts (MoTE) to leverage both semantic and data distributional shifts to learn and adapt temporal trends into classification models. Our analysis shows classification performance varies over time across different languages, and we experimentally demonstrate that MoTE can enhance classifier generalizability over temporal data shifts. Our study provides analytic insights and addresses the need for time-aware models that perform robustly in multilingual scenarios.