edit

Quickstart

Step 1: Preprocess the data

python preprocess.py -train_src data/src-train.txt -train_tgt data/tgt-train.txt -valid_src data/src-val.txt -valid_tgt data/tgt-val.txt -save_data data/demo

We will be working with some example data in data/ folder.

The data consists of parallel source (src) and target (tgt) data containing one sentence per line with tokens separated by a space:

  • src-train.txt
  • tgt-train.txt
  • src-val.txt
  • tgt-val.txt

Validation files are required and used to evaluate the convergence of the training. It usually contains no more than 5000 sentences.

$ head -n 3 data/src-train.txt
It is not acceptable that , with the help of the national bureaucracies , Parliament 's legislative prerogative should be made null and void by means of implementing provisions whose content , purpose and extent are not laid down in advance .
Federal Master Trainer and Senior Instructor of the Italian Federation of Aerobic Fitness , Group Fitness , Postural Gym , Stretching and Pilates; from 2004 , he has been collaborating with Antiche Terme as personal Trainer and Instructor of Stretching , Pilates and Postural Gym .
" Two soldiers came up to me and told me that if I refuse to sleep with them , they will kill me . They beat me and ripped my clothes .

After running the preprocessing, the following files are generated:

  • demo.src.dict: Dictionary of source vocab to index mappings.
  • demo.tgt.dict: Dictionary of target vocab to index mappings.
  • demo.train.pt: serialized PyTorch file containing vocabulary, training and validation data

The *.dict files are needed to check or reuse the vocabularies. These files are simple human-readable dictionaries.

$ head -n 10 data/demo.src.dict
<blank> 1
<unk> 2
<s> 3
</s> 4
It 5
is 6
not 7
acceptable 8
that 9
, 10
with 11

Internally the system never touches the words themselves, but uses these indices.

Step 2: Train the model

python train.py -data data/demo.train.pt -save_model demo-model 

The main train command is quite simple. Minimally it takes a data file and a save file. This will run the default model, which consists of a 2-layer LSTM with 500 hidden units on both the encoder/decoder. You can also add -gpus 1 to use (say) GPU 1.

Step 3: Translate

python translate.py -model demo-model_epochX_PPL.pt -src data/src-test.txt -output pred.txt -replace_unk -verbose

Now you have a model which you can use to predict on new data. We do this by running beam search. This will output predictions into pred.txt.

Note

The predictions are going to be quite terrible, as the demo dataset is small. Try running on some larger datasets! For example you can download millions of parallel sentences for translation or summarization.