THUMT: An Open Source Toolkit for Neural Machine Translation

Code

• github.com/thunlp-mt/ckd
  pytorch★ 1
• github.com/wangmz15/Chinese-Error-Correction-with-THUMT
  tf★ 0
• github.com/insigh/THUMT
  tf★ 0
• github.com/Glaceon31/Document-Transformer
  tf★ 0

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.

Tasks

Reproductions