Metadata-Version: 2.1
Name: openue
Version: 0.0.2
Summary: Universal extractor for text.
Home-page: https://github.com/zxlzr/openue
Author: zxlzr
Author-email: jack16900@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# OpenUE
OpenUE is an open-source and extensible toolkit that provides a off-the-shelf framework to implement a  plethora of extraction tasks.

You can refer to our [document](https://openue-docs.readthedocs.io/en/latest/) for more details about this project.

# Getting Started

Requirement

conda -r openue 

python -r requirement.txt 

sh preprocess

sh train_

sh predict.sh 

python gen_triple.py

#Serving 


## Joint Entity and  Relation Extraction


table


## Joint Slot Filing  and  Intent Classification

table

## Joint Opinion  and  Sentiment Classification

table 

## Install 

### Install as A Python Package

We are now working on deploy OpenUE as a Python package. Coming soon!

### Using Git Repository

Clone the repository from our github page (don't forget to star us!)

```bash
git clone https://github.com/zxlzr/OpenUE.git
```

If it is too slow, you can try
```
git clone https://github.com/zxlzr/OpenUE.git --depth 1
```

Then install all the requirements:

```
pip install -r requirements.txt
```

Then install the package with 
```
python setup.py install 
```

## Tools

```python
>>> import openuee
>>> model = openue.get_model('ske_bert_entity_relation')
```
Note that it may take a few minutes to download checkpoint and data for the first time. Then use `infer` to do sentence-level entity and relation extraction

```python




## How to Cite

If you use or extend our work, please cite the following paper:

```
@inproceedings{zhang-2020-opennue,
    title = "{O}pe{UE}: An Open and Extensible Toolkit for Universal  Extraction in Text",
    author = "Ningyu Zhang, Shumin Deng, Huajun Chen",
    year = "2020",
}
```


