Is it possible to train with just src, mt, ter?

[unbabel]

Is it possible to train with just src, mt, ter?

[captainvera]

Hi James!

Although this was something we never considered, we did have some requests about that and we added that functionality. This is the reason why all of the examples assume you would have more data. However, as I mentioned, you can train with just src, mt and TER.

To do so you need to specify the following in your config file (besides the rest of the parameters):

sentence-level: True
predict-gaps: False
predict-target: False
predict-source: False

Keep in mind that there are some config options based on word-level tags that might not work when training just for sentence-level.

Let us know if you find any errors while training only with sentences!
Miguel

[captainvera]

Closing this since there have been no updates, feel free to re-open if you have further questions!

[jimbogill]

Thanks Miguel. I successfully trained a predictor-estimator model on WMT data following your advice. I did this using a modified version of the config file in the experiments directory. In case it's useful, here are the modifications I made:

OpenKiwi/experiments/train_estimator.yaml

Line 32 in 715eba7

sentence-level: False

Changed to true

OpenKiwi/experiments/train_estimator.yaml

Line 46 in 715eba7

predict-target: true

Changed to false

OpenKiwi/experiments/train_estimator.yaml

Line 108 in 715eba7

train-target-tags: data/WMT17/word_level/train.tags

Changed to train-sentence-scores

OpenKiwi/experiments/train_estimator.yaml

Line 114 in 715eba7

valid-target-tags: data/WMT17/word_level/dev.tags

Changed to valid-sentence-scores