As there is a collocation for numbers in nltk such as ('RS', '##number##')
I'm wondering if there is such a specifier for Roman numerals which I want to use for something like this: ('volume', '##roman number##')
If there is no way to do such a thing, it would be helpful if there was a viable way to convert Roman numerals to decimal for sentence segmentation, and then after segmentation convert the text back to the original Roman numerals.
