---
title: NER-PMR-Large
canonical_url: "https://www.modelscope.cn/models/iic/NER-PMR-Large"
md_url: "https://www.modelscope.cn/models/iic/NER-PMR-Large.md"
repository: iic/NER-PMR-Large
chinese_name: "基于NER微调的机器阅读理解模型"
last_updated: 2023-09-27
license: "Apache License 2.0"
pipeline_tag: named-entity-recognition
tasks:
  - named-entity-recognition
model_type:
  - structbert
architectures:
  - RoBERTa_PMR
library_name:
  - pytorch
frameworks:
  - PyTorch
language:
  - en
domain:
  - nlp
downloads: 74
stars: 0
tags:
  - Alibaba
  - NER
  - "NeurIPS 2023"
  - "信息抽取"
---

# NER-PMR-Large

> NER-PMR-Large - iic 在 ModelScope 开源的模型。NER-PMR-large从PMR-large初始化而来，并在下游4个NER训练数据上进行微调，包括CoNLL, WNUT17, ACE2004，ACE2005.

iic/NER-PMR-Large 是 ModelScope 魔搭社区上的named-entity-recognition模型，采用 Apache License 2.0 许可。

- **Repository**: iic/NER-PMR-Large
- **License**: Apache License 2.0
- **Tasks**: named-entity-recognition
- **Tags**: Alibaba, NER, NeurIPS 2023, 信息抽取
- **Downloads**: 74
- **Stars**: 0
- **Last updated**: 2023-09-27

Source: https://www.modelscope.cn/models/iic/NER-PMR-Large

---

## NER-PMR-large
NER-PMR-large is initialized with [PMR-large](https://huggingface.co/DAMO-NLP-SG/PMR-large) and further fine-tuned with 4 NER training data, namely [CoNLL](https://huggingface.co/datasets/conll2003), [WNUT17](https://huggingface.co/datasets/wnut_17), [ACE2004](https://paperswithcode.com/sota/nested-named-entity-recognition-on-ace-2004), and [ACE2005](https://paperswithcode.com/sota/nested-named-entity-recognition-on-ace-2005).

The model performance on the test sets are: 

||  CoNLL | WNUT17 | ACE2004 | ACE2005 |
|--|------------|-----------|----------|--|
|RoBERTa-large (single-task model)|  92.8 | 57.1 | 86.3|87.0|
|PMR-large  (single-task model)|   93.6 | 60.8 | 87.5 | 87.4|
|NER-PMR-large  (multi-task model)|   92.9   | 54.7| 87.8| 88.4|

Note that the performance of RoBERTa-large and PMR-large are single-task fine-tuning, while NER-PMR-large is a multi-task fine-tuned model. 
As it is fine-tuned on multiple datasets, we believe that NER-PMR-large has a better generalization capability to other NER tasks than PMR-large and RoBERTa-large.


### How to use
You can try the codes from [this repo](https://github.com/DAMO-NLP-SG/PMR/NER) for both training and inference.


### BibTeX entry and citation info
```bibtxt
@article{xu2022clozing,
  title={From Clozing to Comprehending: Retrofitting Pre-trained Language Model to Pre-trained Machine Reader},
  author={Xu, Weiwen and Li, Xin and Zhang, Wenxuan and Zhou, Meng and Bing, Lidong and Lam, Wai and Si, Luo},
  journal={arXiv preprint arXiv:2212.04755},
  year={2022}
}
```