I'm looking for spanish word vectors (preferably word2vec output format) to use in a scala nlp application. I've tried the ones on https://github.com/uchile-nlp/spanish-word-embeddings, but they are either in the wrong language, missing headers (not the desired word2vec output format) or for some reason I'm not able to load the model correctly. I'm using word2vecscala (https://github.com/trananh/word2vec-scala) to load the vectors. Any recommendations would be much appreciated.

  • Why don't you train your own W2V model on Spanish Wikipedia?
    – user8811
    May 28 '19 at 18:15
  • Because I would have to use spark or some other ml library to load and use the vectors wouldn't I? I was hoping to find something ready-made and light-weight. I guess I could train, then try to find something light-weight to parse and load the output. Any ideas?
    – Boris
    May 30 '19 at 9:48
  • If using Scala is not a must for you, you could easily train and load the model in Python using Gensim
    – user8811
    May 31 '19 at 12:22
  • I was looking for a way to do it in scala so as to integrate it into existing software.
    – Boris
    May 31 '19 at 13:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.