486
this post was submitted on 17 Aug 2023
486 points (96.0% liked)
Technology
59232 readers
3464 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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.
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.
I'm sorry you failed to grasp how it works in this context.
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.
Try asking it how the vectorization of king and queen are related.