Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition
This addresses a specific discrepancy in few-shot named entity recognition for NLP researchers, but it is incremental as it builds on existing paradigms.
The paper tackled the problem of embeddings from pre-trained models biasing prototypical neural networks in few-shot named entity recognition, proposing a normalization method that showed superiority over counterpart models and was comparable to state-of-the-art methods on nine benchmark datasets.
Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition. Existing methods, unfortunately, are not aware of the fact that embeddings from pre-trained models contain a prominently large amount of information regarding word frequencies, biasing prototypical neural networks against learning word entities. This discrepancy constrains the two models' synergy. Thus, we propose a one-line-code normalization method to reconcile such a mismatch with empirical and theoretical grounds. Our experiments based on nine benchmark datasets show the superiority of our method over the counterpart models and are comparable to the state-of-the-art methods. In addition to the model enhancement, our work also provides an analytical viewpoint for addressing the general problems in few-shot name entity recognition or other tasks that rely on pre-trained models or prototypical neural networks.