# GraphWriter

**Repository Path**: silence98/GraphWriter

## Basic Information

- **Project Name**: GraphWriter
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-11-02
- **Last Updated**: 2021-11-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Text Generation from Knowledge Graphs with Graph Transformers

This repository contains the source code of our paper, [Text Generation from Knowledge Graphs with Graph Transformers](https://arxiv.org/abs/1904.02342), which is accepted for publication at [NAACL 2019](http://naacl2019.org/).

# Instructions
Environment：
```
conda create -n py37 python=3.7
pip install torch==1.6 dill torchtext==0.6
pip install allennlp
```
BUGS:
```
OrderedDict importError: python>= 3.7.2?
lengths: https://blog.csdn.net/weixin_43711726/article/details/112246264
```


Training:
```
python train.py -save <DIR>
```
Use ``--help`` for a list of all training options.

To generate, use 
```
python generator.py -save <SAVED MODEL>
``` 
with the appropriate model flags used to train the model

To evaluate, run
```
python eval.py <GENERATED TEXTS> <GOLD TARGETS>
```


# AGENDA Dataset

The AGENDA dataset is available in a user-friendly json format in /data/unprocessed.tar.gz
Preprocessed data is also available in /data.


## Citation
If this work is useful in your research, please cite our paper.
```
@inproceedings{koncel2019text,
  title={{T}ext {G}eneration from {K}nowledge {G}raphs with {G}raph {T}ransformers},
  author={Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, and Hannaneh Hajishirzi},
  booktitle={NAACL},
  year={2019}
}
```