To apply the same tokenisation style to unlabelled data for semi-supervised learning it would be great to find more detail on the tokenisation, either what standard is followed or how to run the tokeniser on one's own input, without having to understand sea/lib/nlp.py.
To apply the same tokenisation style to unlabelled data for semi-supervised learning it would be great to find more detail on the tokenisation, either what standard is followed or how to run the tokeniser on one's own input, without having to understand `sea/lib/nlp.py`.
To apply the same tokenisation style to unlabelled data for semi-supervised learning it would be great to find more detail on the tokenisation, either what standard is followed or how to run the tokeniser on one's own input, without having to understand
sea/lib/nlp.py
.