Federated Named Entity Recognition

TL;DR

This paper evaluates federated learning for Named-Entity Recognition, demonstrating near-centralized performance with some degradation in heterogeneous environments, and discusses challenges and future research directions.

Contribution

It provides an empirical analysis of federated learning's effectiveness for NER using a standard dataset and model, highlighting convergence and challenges.

Findings

Federated training achieves near-centralized NER performance.

Performance degrades with increased data heterogeneity.

Convergence rate of federated NER models is analyzed.

Abstract

We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the language-independent CoNLL-2003 dataset as our benchmark dataset and a Bi-LSTM-CRF model as our benchmark NER model. We show that federated training reaches almost the same performance as the centralized model, though with some performance degradation as the learning environments become more heterogeneous. We also show the convergence rate of federated models for NER. Finally, we discuss existing challenges of Federated Learning for NLP applications that can foster future research directions.