metadata
license: cc-by-nc-4.0
language:
- en
UniNER-7B-type-sup
Description: This model was trained on the combination of two data sources: (1) ChatGPT-generated Pile-NER-type data, and (2) 40 supervised datasets in the Universal NER benchmark (see Fig. 4 in paper), where we randomly sample 10K instances from the train split of each dataset. Note that CrossNER and MIT datasets are excluded from training for OOD evaluation.
Check our paper for more information. Check our repo about how to use the model.
Inference
The template for inference instances is as follows:
Prompting template:
A virtual assistant answers questions from a user based on the provided text.
USER: Text: {Fill the input text here}
ASSISTANT: I’ve read this text.
USER: What describes {Fill the entity type here} in the text?
ASSISTANT: (model's predictions in JSON format)
A virtual assistant answers questions from a user based on the provided text.
USER: Text: {Fill the input text here}
ASSISTANT: I’ve read this text.
USER: What describes {Fill the entity type here} in the text?
ASSISTANT: (model's predictions in JSON format)
Note: Inferences are based on one entity type at a time. For multiple entity types, create separate instances for each type.
License
This model and its associated data are released under the CC BY-NC 4.0 license. They are primarily used for research purposes.
Citation
@article{zhou2023universalner,
title={UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition},
author={Wenxuan Zhou and Sheng Zhang and Yu Gu and Muhao Chen and Hoifung Poon},
year={2023},
eprint={2308.03279},
archivePrefix={arXiv},
primaryClass={cs.CL}
}