Mix of Experts Language Model for Named Entity Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914777361547264 |
|---|---|
| author | Chen, Xinwei Li, Kun Song, Tianyou Guo, Jiangjian |
| author_facet | Chen, Xinwei Li, Kun Song, Tianyou Guo, Jiangjian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_19192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mix of Experts Language Model for Named Entity Recognition Chen, Xinwei Li, Kun Song, Tianyou Guo, Jiangjian Computation and Language Artificial Intelligence 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. |
| title | Mix of Experts Language Model for Named Entity Recognition |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.19192 |