[tcwc]

Neat idea! It looks like the NLTK POS tagger is having trouble here so might limit your recall when used as a filter.

Instead I wonder if it would be better to use the context of each token to mine significant ngrams from the rest of Shakespeare's work and filter for rhymes with a phoenetic hash like Metaphone.

[garysieling]

Interesting thought, thanks! I was thinking an approach like that would be good for non-dictionary words.

One of the things I didn't go in detail in is the issue where there are multiple pronunciations for a word - I was thinking that the way to address that would be to compare pronunciations between lines, but looking at metaphones across Shakespeare's work overall might also help build a solution to that.