test
This commit is contained in:
parent
cda56a6ace
commit
d2c7e7eb15
16
README.md
16
README.md
|
@ -80,24 +80,14 @@ DeepKE 提供了多种知识抽取模型。
|
|||
|
||||
2. NER
|
||||
|
||||
数据为txt文件
|
||||
|
||||
中文样式范例为:
|
||||
数据为txt文件,样式范例为:
|
||||
|
||||
| Sentence | Person | Location | Organization |
|
||||
| :----------------------------------------------------------: | :------------------------: | :----------: | :----------------------------: |
|
||||
| :----------------------------------------------------------: | :------------------------: | :----------: | :----------------------------: |
|
||||
| 本报北京9月4日讯记者杨涌报道:部分省区人民日报宣传发行工作座谈会9月3日在4日在京举行。 | 杨涌 | 北京,京 | 人民日报 |
|
||||
| 《红楼梦》是中央电视台和中国电视剧制作中心根据中国古典文学名著《红楼梦》摄制于1987年的一部古装连续剧,由王扶林导演,周汝昌、王蒙、周岭等多位红学家参与制作。 | 王扶林,周汝昌,王蒙,周岭 | / | 中央电视台,中国电视剧制作中心 |
|
||||
| 秦始皇兵马俑位于陕西省西安市,1961年被国务院公布为第一批全国重点文物保护单位,是世界八大奇迹之一。 | 秦始皇 | 陕西省西安市 | 国务院 |
|
||||
|
||||
英文样式范例为:
|
||||
|
||||
| Sentence | Person | Location | Organization | Miscellaneous |
|
||||
| :----------------------------------------------------------: | :----------------------------------: | :---------------: | :-------------------------: | :-------------------: |
|
||||
| Australian Tom Moody took six for 82 but Chris Adams, 123, and Tim O'Gorman, 109, took Derbyshire to 471 and a first innings lead of 233. | Tom Moody, Chris Adams, Tim O'Gorman | / | Derbysire | Australian |
|
||||
| Irene, a master student in Zhejiang University, Hangzhou, is traveling in Warsaw for Chopin Music Festival. | Irene | Hangzhou, Warsaw | Zhejiang University | Chopin Music Festival |
|
||||
| It was one o'clock when we left Lauriston Gardens and Sherlock Holmes led me to Metropolitan Police Service. | Sherlock Holmes | Lauriston Gardens | Metropolitan Police Service | / |
|
||||
|
||||
|
||||
具体流程请进入详细的README中:
|
||||
|
||||
**[STANDARD](https://github.com/zjunlp/deepke/blob/test_new_deepke/example/ner/standard)**
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
# 快速上手
|
||||
## 快速上手
|
||||
|
||||
## 环境依赖
|
||||
### 环境依赖
|
||||
|
||||
> python >= 3.7
|
||||
|
||||
|
@ -9,10 +9,11 @@
|
|||
- seqeval==0.0.5
|
||||
- tqdm==4.31.1
|
||||
- nltk==3.4.5
|
||||
- deepke
|
||||
|
||||
|
||||
|
||||
## 克隆代码
|
||||
### 克隆代码
|
||||
|
||||
```
|
||||
git clone git@github.com:zjunlp/DeepKE.git
|
||||
|
@ -20,7 +21,7 @@ git clone git@github.com:zjunlp/DeepKE.git
|
|||
|
||||
|
||||
|
||||
## 使用pip安装
|
||||
### 使用pip安装
|
||||
|
||||
首先创建python虚拟环境,再进入虚拟环境
|
||||
|
||||
|
@ -28,9 +29,9 @@ git clone git@github.com:zjunlp/DeepKE.git
|
|||
|
||||
|
||||
|
||||
## 使用数据进行训练预测
|
||||
### 使用数据进行训练预测
|
||||
|
||||
- 存放数据:在`data`文件夹下存放数据集。主要有三个文件:
|
||||
- 存放数据:在`data`文件夹下存放数据。主要有三个文件:
|
||||
- `train.txt`:存放训练数据集
|
||||
- `valid.txt`:存放验证数据集
|
||||
- `test.txt`:存放测试数据集
|
||||
|
@ -40,7 +41,9 @@ git clone git@github.com:zjunlp/DeepKE.git
|
|||
|
||||
- 进行预测 ```python predict.py```
|
||||
|
||||
## 模型内容
|
||||
|
||||
BERT
|
||||
|
||||
### 模型内容
|
||||
|
||||
1、BERT
|
||||
|
||||
|
|
|
@ -1,2 +1,3 @@
|
|||
from .attribution_extraction import *
|
||||
from .relation_extraction import *
|
||||
from .relation_extraction import *
|
||||
from .name_entity_re import *
|
|
@ -0,0 +1 @@
|
|||
from .standard import *
|
|
@ -0,0 +1,2 @@
|
|||
from .BasicNer import Ner
|
||||
from .InferBert import Ner
|
|
@ -0,0 +1,3 @@
|
|||
from .dataset import *
|
||||
from .preprocess import *
|
||||
from .trainer import *
|
|
@ -2,16 +2,13 @@ class InputExample(object):
|
|||
"""A single training/test example for simple sequence classification."""
|
||||
|
||||
def __init__(self, guid, text_a, text_b=None, label=None):
|
||||
"""Constructs a InputExample.
|
||||
|
||||
Args:
|
||||
guid: Unique id for the example.
|
||||
text_a: string. The untokenized text of the first sequence. For single
|
||||
sequence tasks, only this sequence must be specified.
|
||||
text_b: (Optional) string. The untokenized text of the second sequence.
|
||||
Only must be specified for sequence pair tasks.
|
||||
label: (Optional) string. The label of the example. This should be
|
||||
specified for train and dev examples, but not for test examples.
|
||||
"""
|
||||
Constructs a InputExample.
|
||||
Args:
|
||||
guid(string): Unique id for the example.
|
||||
text_a(string): The untokenized text of the first sequence. For single sequence tasks, only this sequence must be specified.
|
||||
text_b(string, optional): The untokenized text of the second sequence. Only must be specified for sequence pair tasks.
|
||||
label(string, optional): The label of the example. This should be specified for train and dev examples, but not for test examples.
|
||||
"""
|
||||
self.guid = guid
|
||||
self.text_a = text_a
|
|
@ -1,6 +1,6 @@
|
|||
import sys
|
||||
sys.path.append("..")
|
||||
from models.BERTNER import Ner
|
||||
from models.InferBert import Ner
|
||||
model = Ner("out_ner/")
|
||||
|
||||
text= "Irene, a master student in Zhejiang University, Hangzhou, is traveling in Warsaw for Chopin Music Festival."
|
|
@ -23,7 +23,7 @@ from seqeval.metrics import classification_report
|
|||
from dataset import *
|
||||
from preprocess import *
|
||||
sys.path.append("..")
|
||||
from models.NER import Ner
|
||||
from tools.BasicNer import Ner
|
||||
|
||||
|
||||
def main():
|
Loading…
Reference in New Issue