metadata

language:
  - zh
tags:
  - named entity recognition
license: apache-2.0
datasets:
  - CMeEE
metrics:
  - micro f1

Global Pointer实体抽取模型

模型介绍

数据集：CMeEE中文医学文本命名实时识别
模型方法：Efficient GlobalPointer：少点参数，多点效果

使用方法

pip install litie

from pprint import pprint
from litie.pipelines import NerPipeline

pipline = NerPipeline("global-pointer", model_name_or_path="xusenlin/cmeee-global-pointer")
text = "可伴发血肿或脑梗死而出现局灶性神经体征，如肢体瘫痪及颅神经异常等。"
pprint(pipline(text))

更多模型的训练和推理详见 lit-ie