OpenNMT: Open-Source Neural Machine Translation

This is a Pytorch port of OpenNMT, an open-source (MIT) neural machine translation system.

Quickstart

Some useful tools:

The example below uses the Moses tokenizer (http://www.statmt.org/moses/) to prepare the data and the moses BLEU script for evaluation.

wget https://raw.githubusercontent.com/moses-smt/mosesdecoder/master/scripts/tokenizer/tokenizer.perl
wget https://raw.githubusercontent.com/moses-smt/mosesdecoder/master/scripts/share/nonbreaking_prefixes/nonbreaking_prefix.de
wget https://raw.githubusercontent.com/moses-smt/mosesdecoder/master/scripts/share/nonbreaking_prefixes/nonbreaking_prefix.en
sed -i "s/$RealBin\/..\/share\/nonbreaking_prefixes//" tokenizer.perl
wget https://raw.githubusercontent.com/moses-smt/mosesdecoder/master/scripts/generic/multi-bleu.perl

WMT'16 Multimodal Translation: Multi30k (de-en)

An example of training for the WMT'16 Multimodal Translation task (http://www.statmt.org/wmt16/multimodal-task.html).

0) Download the data.

mkdir -p data/multi30k
wget http://www.quest.dcs.shef.ac.uk/wmt16_files_mmt/training.tar.gz &&  tar -xf training.tar.gz -C data/multi30k && rm training.tar.gz
wget http://www.quest.dcs.shef.ac.uk/wmt16_files_mmt/validation.tar.gz && tar -xf validation.tar.gz -C data/multi30k && rm validation.tar.gz
wget https://staff.fnwi.uva.nl/d.elliott/wmt16/mmt16_task1_test.tgz && tar -xf mmt16_task1_test.tgz -C data/multi30k && rm mmt16_task1_test.tgz

1) Preprocess the data.

for l in en de; do for f in data/multi30k/*.$l; do if [[ "$f" != *"test"* ]]; then sed -i "$ d" $f; fi;  done; done
for l in en de; do for f in data/multi30k/*.$l; do perl tokenizer.perl -a -no-escape -l $l -q  < $f > $f.atok; done; done
python preprocess.py -train_src data/multi30k/train.en.atok -train_tgt data/multi30k/train.de.atok -valid_src data/multi30k/val.en.atok -valid_tgt data/multi30k/val.de.atok -save_data data/multi30k.atok.low -lower

2) Train the model.

python train.py -data data/multi30k.atok.low.train.pt -save_model multi30k_model -gpus 0

3) Translate sentences.

python translate.py -gpu 0 -model multi30k_model_e13_*.pt -src data/multi30k/test.en.atok -tgt data/multi30k/test.de.atok -replace_unk -verbose -output multi30k.test.pred.atok

4) Evaluate.

perl multi-bleu.perl data/multi30k/test.de.atok < multi30k.test.pred.atok

Pretrained Models

The following pretrained models can be downloaded and used with translate.py (These were trained with an older version of the code; they will be updated soon).

• onmt_model_en_de_200k: An English-German translation model based on the 200k sentence dataset at OpenNMT/IntegrationTesting. Perplexity: 21.
• onmt_model_en_fr_b1M: An English-French model trained on benchmark-1M. Perplexity: 4.85.

Release Notes

The following OpenNMT features are implemented:

• multi-layer bidirectional RNNs with attention and dropout
• data preprocessing
• saving and loading from checkpoints
• inference (translation) with batching and beam search

Not yet implemented:

• word features
• multi-GPU
• residual connections