# Pointer_Transformer_Generator_Summary

**Repository Path**: cngaoxl/Pointer_Transformer_Generator_Summary

## Basic Information

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

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-06-01
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Pointer_Transformer_Generator tensorflow 2.0.0

For the abstractive summarization task, I wanted to experiment the transformer model. I recreated a transformer model (thanks to tensorflow transformer tutorial) and added a pointer module (have a look at this paper for more informations on the pointer generator network : https://arxiv.org/abs/1704.04368 ).

Please follow the next steps to launch the project :

## Step 1 : The data

Transform the data to tfrecords format。 (chunk files format : tfrecords)


## Step 2 : launch the project : 

**python main.py --max_enc_len=400 \ <br>
--max_dec_len=100 \ <br>
--batch_size=16 \ <br>
--vocab_size=50000 \ <br>
--num_layers=3 \ <br>
--model_depth=512 \ <br>
--num_heads=8 \ <br>
--dff=2048 \ <br>
--seed=123 \ <br>
--log_step_count_steps=1 \ <br>
--max_steps=230000 \ <br>
--mode=train \ <br>
--save_summary_steps=10000 \ <br>
--checkpoints_save_steps=10000 \ <br>
--model_dir=model_folder \ <br>
--data_dir=data_folder \ <br>
--vocab_path=vocab \ <br>**

PS : Feel free to change some of the hyperparameters<br>
python main.py --help , for more details on the hyperparameters



## Requirements
- python >= 3.6
- tensorflow 2.0.0
- argparse
- os
- glob
- numpy