readme
This commit is contained in:
parent
48ccce9cf5
commit
b9f3f590ef
|
@ -78,7 +78,8 @@ DeepKE包括了三个模块,可以进行关系抽取、实体命名识别以
|
|||
常规模块为预训练模型,可进入其目录,修改数据集以及conf文件夹下的目录,```python run.py```即可训练,```python predict.py```即可预测。
|
||||
|
||||
|
||||
**[FEW-SHOT](https://github.com/zjunlp/DeepKE/tree/test_new_deepke/example/ner/few-shot)**
|
||||
**[FEW-SHOT](https://github.com/zjunlp/DeepKE/tree/test_new_deepke/example/ner/few-shot)** :
|
||||
少样本模块使用了LightNER模型,可进入其目录,模型加载和保存位置以及配置可以在shell脚本中修改```bash run_conll2003.sh```训练conll2003,```bash run_fewshot.sh "mit-movie" False```不加载模型,直接进行few-shot训练,```bash run_fewshot.sh "mit-movie" True```加载模型,进行few-shot训练,```bash run_predict.sh```进行预测。
|
||||
|
||||
|
||||
3. AE
|
||||
|
|
Loading…
Reference in New Issue