Summary
In this chapter, we went through three additional essential aspects of the original Transformer.
We started by defining machine translation. Human translation sets a very high baseline for machines to reach. We saw that English-French and English-German translations imply quite an amount of problems to solve. The Transformer tackled these problems and set state-of-the-art BLEU records to beat.
We then preprocessed a WMT French-English dataset from the European Parliament that required cleaning. We had to transform the datasets into lines and clean the data up. Once that was done, we reduced the dataset's size by suppressing words that occurred below a frequency threshold.
Machine translation NLP models require identical evaluation methods. Training a model on a WMT dataset requires BLEU evaluations. We saw that geometric assessments are a good basis to score translations but even modified BLEU has its limits. We thus added a smoothing technique to enhance...
