THUMT: An Open Source Toolkit for Neural Machine Translation
arXiv:1706.06415
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.
4 pages, 1 figure
References in corpus (3)
Cited by in corpus (6)
- Convolutional Self-Attention Networks
- Shared-Private Bilingual Word Embeddings for Neural Machine Translation
- MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora
- Neuron Interaction Based Representation Composition for Neural Machine Translation
- Learning to Copy for Automatic Post-Editing
- Learning to Detect Unacceptable Machine Translations for Downstream Tasks