https://github.com/keon/seq2seq

Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch
https://github.com/keon/seq2seq

deep-learning machine-translation seq2seq

Last synced: 3 months ago
JSON representation

Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch

• Host: GitHub
• URL: https://github.com/keon/seq2seq
• Owner: keon
• License: mit
• Archived: true
• Created: 2017-12-02T11:42:18.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2020-12-13T10:53:01.000Z (almost 4 years ago)
• Last Synced: 2024-04-20T10:32:41.294Z (7 months ago)
• Topics: deep-learning, machine-translation, seq2seq
• Language: Python
• Homepage:
• Size: 31.3 KB
• Stars: 683
• Watchers: 15
• Forks: 172
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-pytorch-list-CNVersion - minimal-seq2seq
• Awesome-pytorch-list - minimal-seq2seq

README

        
# mini seq2seq

Minimal Seq2Seq model with attention for neural machine translation in PyTorch.

This implementation focuses on the following features:

- Modular structure to be used in other projects

- Minimal code for readability

- Full utilization of batches and GPU.

This implementation relies on [torchtext](https://github.com/pytorch/text) to minimize dataset management and preprocessing parts.

## Model description

* Encoder: Bidirectional GRU

* Decoder: GRU with Attention Mechanism

* Attention: [Neural Machine Translation by Jointly Learning to Align and Translate](https://arxiv.org/abs/1409.0473)

![](http://www.wildml.com/wp-content/uploads/2015/12/Screen-Shot-2015-12-30-at-1.16.08-PM.png)

## Requirements

* GPU & CUDA

* Python3

* PyTorch

* torchtext

* Spacy

* numpy

* Visdom (optional)

download tokenizers by doing so:

```

python -m spacy download de

python -m spacy download en

```

## References

Based on the following implementations

* [PyTorch Tutorial](http://pytorch.org/tutorials/intermediate/seq2seq_translation_tutorial.html)

* [@spro/practical-pytorch](https://github.com/spro/practical-pytorch)

* [@AuCson/PyTorch-Batch-Attention-Seq2seq](https://github.com/AuCson/PyTorch-Batch-Attention-Seq2seq)