THUMT: An Open Source Toolkit for Neural Machine Translation

TL;DR

THUMT is an open-source neural machine translation toolkit that supports various training methods, visualization, and demonstrates superior performance on Chinese-English translation tasks.

Contribution

It introduces a versatile NMT toolkit with multiple training criteria, visualization tools, and achieves improved translation quality over existing toolkits.

Findings

Minimum risk training improves translation quality.

THUMT outperforms GroundHog on Chinese-English datasets.

Visualization aids in analyzing neural network internals.

Abstract

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.