We've been using mostly contextual vectors (BERT based models) and working in english (vast majority of our projects) and italian.
We've been using word2vec embeddings for a Lucene contribution for machine-learned synonyms. Cheers On Thu, 9 Mar 2023, 16:03 Daniel Benito, <[email protected]> wrote: > Hi everyone, > > I'm new to the list, so I apologize if this has been asked before (I > looked through the archives but couldn't find anything). > > I'm interested in hearing from other Solr users who are working with text > embeddings using the dense vector search functionality in Solr. > > For those who are, I have a couple of questions: > > - Are you using non-contextual (e.g. word2vec, fasText...) or contextual > ones (BERT, ELMO...)? > - What languages are you working with? > > TIA, > > Daniel > > > Daniel Benito | Chief Product Officer | Bitext > e. [email protected] > w. bitext.com > p. +1 480 765 0882 > >
