REVIEW 4 cited by
Mix of Experts Language Model for Named Entity Recognition
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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 trained and ensembled under the Expectation-Maximization (EM) framework, so that noisy supervision can be dramatically alleviated. In addition, we introduce a fair assignment module to balance the document-model assignment process. Extensive experiments on real-world datasets show that the proposed method achieves state-of-the-art performance compared with other distantly supervised NER.
Forward citations
Cited by 4 Pith papers
-
Intelligent logistics management robot path planning algorithm integrating transformer and GCN network
This paper reports a Transformer-plus-GNN-plus-GAN path planner with large claimed gains, but lacks the architecture details and experimental evidence to support them.
-
Construction and optimization of health behavior prediction model for the elderly in smart elderly care
A proposed elderly health-prediction platform with standard machine learning components is described, but the paper provides no quantitative experimental evidence for its claimed accuracy.
-
Electronic Health Records-Based Data-Driven Diabetes Knowledge Unveiling and Risk Prognosis
The authors report that a BiLSTM-CRF feature extractor combined with XGBoost and logistic regression outperforms several baseline models for diabetes risk prediction on a private Beijing health-check dataset.
-
Optimized CNNs for Rapid 3D Point Cloud Object Recognition
A 3D point cloud anomaly detection method combining FPFH, multi-view ResNet18 features, and graph convolution reports slightly higher MVTec 3D-AD scores than prior work, but the claimed sparse-convolution and L1 contr...
Discussion (0). Continue with ORCID to comment.