• fkn
    link
    English
    -11 year ago

    This is a misunderstanding on your part. While some neurons are trained this way, word2vec and doc2vec are not these mechanisms. The llms are extensions of these models and while there are certainly some aspects of what you are describing, there is a transcription into vector formats.

    This is the power of vectorization of language (among other things). The one to one mapping between vectors and words / sentences to documents and so forth allows models to describe the distance between words or phrases using euclidian geometry.

    • ayaya
      link
      fedilink
      English
      2
      edit-2
      1 year ago

      I was trying to make it as simple as possible. The format is irrelevant. The model is still storing nothing but weights at the end of the day. Storing the relationships between words and sentences is not the same thing as storing works in a different format which is what your original comment implied.

      • fkn
        link
        English
        -11 year ago

        I’m sorry you failed to grasp how it works in this context.

    • discodoubloon
      link
      fedilink
      01 year ago

      You made me really interested in this concept so I asked GPT-4 what the furthest word away from the word “vectorization” would be.

      Interesting game! If we’re aiming for a word that’s conceptually, contextually, and semantically distant from “vectorization,” I’d pick “marshmallow.” While “vectorization” pertains to complex computational processes and mathematics, “marshmallow” is a soft, sweet confectionery. They’re quite far apart in terms of their typical contexts and meanings.

      It honestly never ceases to surprise me. I’m gonna play around with some more. I do really like the idea that it’s essentially a word calculator.

      • fkn
        link
        English
        31 year ago

        Try asking it how the vectorization of king and queen are related.