This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on top of Theano and supports three training criteria: maximum likelihood estimation, minimum risk training, and semi-supervised training. It features a visualization tool for displaying the relevance between hidden states in neural networks and contextual words, which helps to analyze the internal workings of NMT. Experiments on Chinese-English datasets show that THUMT using minimum risk training significantly outperforms GroundHog, a state-of-the-art toolkit for NMT.
@article{arxiv.1706.06415,
title = {THUMT: An Open Source Toolkit for Neural Machine Translation},
author = {Jiacheng Zhang and Yanzhuo Ding and Shiqi Shen and Yong Cheng and Maosong Sun and Huanbo Luan and Yang Liu},
journal= {arXiv preprint arXiv:1706.06415},
year = {2017}
}