SciVocab Preparation
Opened this issue · 1 comments
kuldeep7688 commented
Can you please elaborate a bit more how you used Sentencepiece to build SciVocab?
ibeltagy commented
It is just one function call: https://github.com/allenai/scibert/blob/master/scripts/cheatsheet.txt#L6
The output format is slightly different than what BERT expects, so we manually fixed after it was generated.