Mix of Experts Language Model for Named Entity Recognition

arXiv:2404.19192v1 Announce Type: new
Abstract: Named Entity Recognition (NER) is an essential steppingstone in the field of natural language processing. Although promising performance has been achieved by various distantly supervised models, we argue that distant supervision inevitably introduces incomplete and noisy annotations, which may mislead the model training process. To address this issue, we propose a robust NER model named BOND-MoE based on Mixture of Experts (MoE). Instead of relying on a single model for NER prediction, multiple models are …

abstract annotations arxiv cs.ai cs.cl experts language language model language processing natural natural language natural language processing ner performance process processing recognition supervision training type