THUMT: An Open Source Toolkit for Neural Machine Translation

Introduction
Online Demo
Implementation
Downloads
History
License
Citation
Development Team
Contributors
Contact

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.

Online Demo

Please click here to play with the online demo.

Implementation

THUMT has currently two main implementations:

THUMT-TensorFlow: a new implementation developed with TensorFlow. It implements the sequence-to-sequence model (Seq2Seq) (Sutskever et al., 2014), the standard attention-based model (RNNsearch) (Bahdanau et al., 2014), and the Transformer model (Transformer) (Vaswani et al., 2017).

THUMT-Theano: the original project developed with Theano, which is no longer updated because MLA put an end to Theano. It implements the standard attention-based model (RNNsearch) (Bahdanau et al., 2014), minimum risk training (MRT) (Shen et al., 2016) for optimizing model parameters with respect to evaluation metrics, semi-supervised training (SST) (Cheng et al., 2016) for exploiting monolingual corpora to learn bi-directional translation models, and layer-wise relevance propagation (LRP) (Ding et al., 2017) for visualizing and anlayzing RNNsearch.

The following table summarizes the features of two implementations:

Implementation	Model	Criterion	Optimizer	LRP
Theano	RNNsearch	MLE, MRT, SST	SGD, Adadelta, Adam	RNNsearch
TensorFlow	Seq2Seq, RNNsearch, Transformer	MLE	Adam	RNNsearch, Transformer

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

Downloads

Stable version

Link	Size	Description	Date
THUMT-TensorFlow-v1.1.tar.gz	286K	The package contains the source code and documentation of the TensorFlow implementation	2018-08-04
THUMT-Theano-v1.02.tar.gz	533K	The package contains the source code and documentation of Theano implementation	2018-01-15

Latest version

Please visit GitHub to obtain the latest version.

History

TensorFlow Implementation:

Version	Size	Updates	Date
v1.1	286K	add layer-wise relevance propagation	2018-08-04
v1.0	269K	First version	2018-01-15

Theano Implementation:

Version	Size	Updates	Date
v1.02	533K	Add learning rate decay policies. Minor bug fix.	2018-01-15
v1.01	530K	Bug fix	2017-07-02
v1.0	529K	First version	2017-06-20

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 thumt17@gmail.com.

Citation

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

Contributors

Zhixing Tan (Xiamen University)

Contact

If you have questions, suggestions and bug reports, please email thumt17@gmail.com.