Is your feature request related to a problem? Please describe.
I want to quickly extend my lookup lists with further values, and want to find further values of records that I didn't even label yet.
Describe the solution you'd like
With a token-based embedding, we should be able to compute n-grams (see below for more context) and compute similarity search based on the entries we already have. That way, we could find synonyms etc. from the corpus we have at hand, which could be super helpful.
Again, this could be something that is actively requested by pressing a button in the lookup list, which then goes on and does the similarity search and creates suggestions.
Describe alternatives you've considered
-
Additional context
Google search for n-grams
An n-gram is a sequence. n-gram. of n words: a 2-gram (which we'll call bigram) is a two-word sequence of words. like “please turn”, “turn your”, or ”your homework”, and a 3-gram (a trigram) is a three-word sequence of words like “please turn your”, or “turn your homework”.
Is your feature request related to a problem? Please describe. I want to quickly extend my lookup lists with further values, and want to find further values of records that I didn't even label yet.
Describe the solution you'd like With a token-based embedding, we should be able to compute n-grams (see below for more context) and compute similarity search based on the entries we already have. That way, we could find synonyms etc. from the corpus we have at hand, which could be super helpful.
Again, this could be something that is actively requested by pressing a button in the lookup list, which then goes on and does the similarity search and creates suggestions.
Describe alternatives you've considered -
Additional context Google search for
n-grams