https://github.com/google/seq2seq

A general-purpose encoder-decoder framework for Tensorflow
https://github.com/google/seq2seq

deeplearning machine-translation neural-network tensorflow translation

Last synced: about 1 month ago
JSON representation

A general-purpose encoder-decoder framework for Tensorflow

• Host: GitHub
• URL: https://github.com/google/seq2seq
• Owner: google
• License: apache-2.0
• Archived: true
• Created: 2017-03-02T22:49:20.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-10-15T08:00:39.000Z (about 4 years ago)
• Last Synced: 2024-09-23T07:33:08.886Z (about 2 months ago)
• Topics: deeplearning, machine-translation, neural-network, tensorflow, translation
• Language: Python
• Homepage: https://google.github.io/seq2seq/
• Size: 1.59 MB
• Stars: 5,607
• Watchers: 245
• Forks: 1,298
• Open Issues: 198
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![CircleCI](https://circleci.com/gh/google/seq2seq.svg?style=svg)](https://circleci.com/gh/google/seq2seq)

---

**[READ THE DOCUMENTATION](https://google.github.io/seq2seq)**

**[CONTRIBUTING](https://google.github.io/seq2seq/contributing/)**

---

A general-purpose encoder-decoder framework for Tensorflow that can be used for Machine Translation, Text Summarization, Conversational Modeling, Image Captioning, and more.

![Translation Model](https://3.bp.blogspot.com/-3Pbj_dvt0Vo/V-qe-Nl6P5I/AAAAAAAABQc/z0_6WtVWtvARtMk0i9_AtLeyyGyV6AI4wCLcB/s1600/nmt-model-fast.gif)

---

The official code used for the [Massive Exploration of Neural Machine Translation Architectures](https://arxiv.org/abs/1703.03906) paper.

If you use this code for academic purposes, please cite it as:

```

@ARTICLE{Britz:2017,

  author          = {{Britz}, Denny and {Goldie}, Anna and {Luong}, Thang and {Le}, Quoc},

  title           = "{Massive Exploration of Neural Machine Translation Architectures}",

  journal         = {ArXiv e-prints},

  archivePrefix   = "arXiv",

  eprinttype      = {arxiv},

  eprint          = {1703.03906},

  primaryClass    = "cs.CL",

  keywords        = {Computer Science - Computation and Language},

  year            = 2017,

  month           = mar,

}

```

This is not an official Google product.