The PyTorch Implementation Of SummaRuNNer
Statement
- Not the official implementation! Just For Learning and communication!
Models
- RNN_RNN
- CNN_RNN
- Hierarchical Attention Networks
Setup
Requires pipenv. Use pip install pipenv if not installed.
pipenv install
pipenv shell
Usage
# train
python main.py -device 0 -batch_size 32 -model RNN_RNN -seed 1 -save_dir checkpoints/XXX.pt
# test
python main.py -device 0 -batch_size 1 -test -load_dir checkpoints/XXX.pt
# predict
python main.py -batch_size 1 -predict -filename x.txt -load_dir checkpoints/RNN_RNN_seed_1.ptpretrained models
- RNN_RNN(
checkpoints/RNN_RNN_seed_1.pt) - CNN_RNN(
checkpoints/CNN_RNN_seed_1.pt) - AttnRNN(
checkpoints/AttnRNN_seed_1.pt)
Result
DailyMail(75 bytes)
| model | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|
| SummaRNNer(Nallapati) | 26.2 | 10.8 | 14.4 |
| RNN-RNN | 26.0 | 11.5 | 13.8 |
| CNN-RNN | 25.8 | 11.3 | 13.8 |
| Hierarchical Attn Net | 26.0 | 11.4 | 13.8 |
Blog
Download Data:
-
百度云:https://pan.baidu.com/s/1LV3iuuH1NjxuAJd0iz14lA 密码:
ivzl -
Google Driver:data.tar.gz
-
Source Data:Neural Summarization by Extracting Sentences and Words
Evaluation
Acknowledge
- Thanks for @AlJohri's and @500swapnil's contribution