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

505 Stars 165 Forks BSD 3-Clause "New" or "Revised" License 130 Commits 15 Opened issues


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

Services available


Need anything else?

Contributors list

THUMT: An Open Source Toolkit for Neural Machine Translation



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:

Online Demo

The online demo of THUMT is available at The languages involved include Ancient Chinese, Arabic, Chinese, English, French, German, Indonesian, Japanese, Portugese, Russian, and Spanish.


THUMT has currently three main implementations:

The following table summarizes the features of three implementations:

| Implementation | Model | Criterion | Optimizer | LRP | Additional Features | | :------------: | :---: | :--------------: | :--------------: | :----------------: | :---------------: | | Theano | RNNsearch | MLE, MRT, SST | SGD, AdaDelta, Adam | RNNsearch | N.A. | | TensorFlow | Seq2Seq, RNNsearch, Transformer | MLE| Adam | RNNsearch, Transformer | Distributed Training, Mixed Precision Training, Gradient Aggregation, Model Ensemble | | PyTorch | Transformer | MLE | SGD, Adadelta, Adam | N.A. | Distributed Training, Mixed Precision Training, Gradient Aggregation, Model Ensemble

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

It is also possible to exploit layer-wise relevance propagation to visualize the relevance between source and target words with THUMT:

Visualization with LRP

Notable Features


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].


Please cite the following paper:

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: Jiacheng Zhang, Yanzhuo Ding, Shiqi Shen, Yong Cheng, Zhixing Tan


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

Derivative Repositories

  • UCE4BT (Improving Back-Translation with Uncertainty-based Confidence Estimation)
  • L2Copy4APE (Learning to Copy for Automatic Post-Editing)
  • Voting4SC (Modeling Voting for System Combination in Machine Translation)
  • 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.