I’ve noticed that one baby step towards this that I like is to be less ‘Markovian’ and try to check if the leaf nodes of the conversation are relevant to their great-great-grandparents or something (really, whatever ancestor it’s easiest to check this for).
I’ve noticed that one baby step towards this that I like is to be less ‘Markovian’ and try to check if the leaf nodes of the conversation are relevant to their great-great-grandparents or something (really, whatever ancestor it’s easiest to check this for).
This is most useful for google docs comment threads.