Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Ying Xiong 9f61528beb | 2 years ago | |
---|---|---|
data | 3 years ago | |
src | 3 years ago | |
README.md | 2 years ago |
python:3.5
tensorflow: 1.11
use machine reading comprehension (MRC) model to solve NER task.
each data is a tuple (question,passage,start_pisition,end_position)
In NER, question is the lable definition for each entity type, passage is each sentence, start_position is the start position of each entity
and end_position is the end position of each entity.
use single one-pass model to solve NER task.
Each data ia a tuple (passage, start_position1, end_position1, start_position2, end_position2, ...)
Because we use the last checkpoint of BERT to predict, so the development set is just to verify the performance of model.
we just set an example for mrc data
we just set an example for SOne data
for SOne model, the type information is defined in advance. For example, normalize_bert.npy is bert representation of guideline information.
get the answer of submit file format
python trans2answer.py
A label-enhanced model for biomedical named entity recogniton (NER)
Python Text Pickle Shell
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》