Reproducibility Study

[KyraGolden]

Dear Jingjing
We are trying to reproduce your experiments from your paper: "Vocabulary Learning via Optimal Transport for Neural Machine Translation" for a University Seminar at the University of Zurich.
And we are looking for the TED multilingual dataset as it was not found in the GitHub repo.
We would also be very grateful if you could make these datasets available:

• TED EN-X data​
• WMT-14 EN-De

Many thanks in advance.

With kind regards,

Kyra & Joëlle

[Jingjing-NLP]

Dear Kyra & Joëlle,

Thanks for your interests! You can refer to "examples/run_ende.sh" to reproduce results on WMT-14 En-De. Due to the large size of WMT-14 EN-De, we do not provide the specific data, instead provide the downloading and processing script. Data can be dowloaded and processed via the script: https://github.com/Jingjing-NLP/VOLT/blob/master/examples/prepare-wmt14en2de.sh. If you need the processed data, I can share you a processed version.

Best,
Jingjing

[Jingjing-NLP]

Dear Jingjing We are trying to reproduce your experiments from your paper: "Vocabulary Learning via Optimal Transport for Neural Machine Translation" for a University Seminar at the University of Zurich. And we are looking for the TED multilingual dataset as it was not found in the GitHub repo. We would also be very grateful if you could make these datasets available:

• TED EN-X data​
• WMT-14 EN-De

Many thanks in advance.

With kind regards,

Kyra & Joëlle

The TED En-X data is stored at https://drive.google.com/drive/folders/1CkcpPu7ovPuvLpCbl1cBLnx510mT0Q2W?usp=sharing