Prompt like:

Extract the company names from the texts below and return as an array

– [“Google”, “Meta”, “Microsoft”]

  • xelldev13@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    You can do this with NER model like bert, is more fast, but is only for entitie recognition

    • name_is_unimportant@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Yeah Named Entity Recognition with BERT works very well, provided that you have a good dataset. Another limitation is that it can only handle 512 tokens