← Open Source
google

seq2seq

A general-purpose encoder-decoder framework for Tensorflow

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
5.62k
Stars
1.28k
Forks
+-1
This week
15
Contributors
Created 2017-03-02 · Updated 2026-10-03 · #5896 today
Top developers
README

CircleCI


READ THE DOCUMENTATION

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


The official code used for the Massive Exploration of Neural Machine Translation Architectures 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.