Need help with THUMT?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

THUNLP-MT
561 Stars 177 Forks BSD 3-Clause "New" or "Revised" License 136 Commits 14 Opened issues

Description

An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group

Services available

!
?

Need anything else?

Contributors list

# 80,603
Python
Tensorf...
neural-...
srl
56 commits
# 119,993
Python
neural-...
TeX
reading...
23 commits
# 209,161
Python
neural-...
machine...
11 commits
# 68,141
reading...
TeX
Python
neural-...
11 commits
# 139,043
Python
neural-...
TeX
reading...
7 commits
# 179,662
text-ge...
reading...
TeX
Python
4 commits
# 271,028
Python
neural-...
TeX
reading...
3 commits
# 99,600
TeX
sed
travis-...
categor...
2 commits
# 420,227
Python
neural-...
machine...
1 commit
# 13,915
TeX
reading...
pytorch
optimiz...
1 commit
# 419,311
Python
neural-...
machine...
1 commit

THUMT: An Open Source Toolkit for Neural Machine Translation

Contents

Introduction

Machine translation is a natural language processing task that aims to translate natural languages using computers automatically. Recent several years have witnessed the rapid development of end-to-end neural machine translation, which has become the new mainstream method in practical MT systems.

THUMT is an open-source toolkit for neural machine translation developed by the Natural Language Processing Group at Tsinghua University. The website of THUMT is: http://thumt.thunlp.org/.

Online Demo

The online demo of THUMT is available at http://translate.thumt.cn/. The languages involved include Ancient Chinese, Arabic, Chinese, English, French, German, Indonesian, Japanese, Portuguese, Russian, and Spanish.

Implementations

THUMT has currently three main implementations:

The following table summarizes the features of three implementations:

| Implementation | Model | Criterion | Optimizer | LRP | | :------------: | :---: | :--------------: | :--------------: | :----------------: | | Theano | RNNsearch | MLE, MRT, SST | SGD, AdaDelta, Adam | RNNsearch | | TensorFlow | Seq2Seq, RNNsearch, Transformer | MLE| Adam | RNNsearch, Transformer | | PyTorch | Transformer | MLE | SGD, Adadelta, Adam | N.A. |

We recommend using THUMT-PyTorch or THUMT-TensorFlow, which delivers better translation performance than THUMT-Theano. We will keep adding new features to THUMT-PyTorch and THUMT-TensorFlow.

Notable Features

  • Transformer (Vaswani et al., 2017)
  • Multi-GPU training & decoding
  • Multi-worker distributed training
  • Mixed precision training & decoding
  • Model ensemble & averaging
  • Gradient aggregation
  • TensorBoard for visualization

Documentation

The documentation of PyTorch implementation is avaiable at here.

License

The source code is dual licensed. Open source licensing is under the BSD-3-Clause, which allows free use for research purposes. For commercial licensing, please email [email protected].

Citation

Please cite the following paper:

Zhixing Tan, Jiacheng Zhang, Xuancheng Huang, Gang Chen, Shuo Wang, Maosong Sun, Huanbo Luan, Yang Liu. THUMT: An Open Source Toolkit for Neural Machine Translation. AMTA 2020.

Jiacheng Zhang, Yanzhuo Ding, Shiqi Shen, Yong Cheng, Maosong Sun, Huanbo Luan, Yang Liu. 2017. THUMT: An Open Source Toolkit for Neural Machine Translation. arXiv:1706.06415.

Development Team

Project leaders: Maosong Sun, Yang Liu, Huanbo Luan

Project members:

Theano: Jiacheng Zhang, Yanzhuo Ding, Shiqi Shen, Yong Cheng

TensorFlow: Zhixing Tan, Jiacheng Zhang, Xuancheng Huang, Gang Chen, Shuo Wang, Zonghan Yang

PyTorch: Zhixing Tan, Gang Chen

Contact

If you have questions, suggestions and bug reports, please email [email protected].

Derivative Repositories

  • UCE4BT (Improving Back-Translation with Uncertainty-based Confidence Estimation)
  • L2Copy4APE (Learning to Copy for Automatic Post-Editing)
  • Document-Transformer (Improving the Transformer Translation Model with Document-Level Context)
  • PR4NMT (Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization)

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.