Federated Named Entity Recognition
This work addresses the challenge of privacy-preserving NLP for distributed data scenarios, but it is incremental as it applies an existing method to a new task.
The paper tackled the problem of applying Federated Learning to Named Entity Recognition, showing that federated training achieves nearly the same performance as centralized models with some degradation in heterogeneous environments, using the CoNLL-2003 dataset and a Bi-LSTM-CRF model.
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.