Closed jhoetter closed 1 year ago
Possible approach: remove all the stop and filler words and then use the POS tags and only keep nouns, verbs, names etc.
This library might be good for keyword extraction https://github.com/vi3k6i5/flashtext
I think that one was a misunderstanding, sorry :-) There are certain algorithms like the YAKE (yet another keyword algorithm), see https://github.com/LIAAD/yake.
The idea is to grab keywords from the existing text
Please describe the module you would like to add to the content library When I have a text, I want to detect only the keywords from it.
Do you already have an implementation? -
Additional context -