NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
Word2Vec-style vector arithmetic on docs embeddings (technicalwriting.dev)
Xx_crazy420_xX 23 hours ago [-]
This is really interesting! I've experimented with similar idea, but with time series forecasting on the sentence embeddings - https://github.com/Srakai/embcaster.

It turns out you can tokenise arbitrary information into constant vector which is really useful for later processing. The vec2text (https://github.com/vec2text/vec2text) is an excellent asset if you want to reverse the embeddings back to text. This allows you to encode arbitrary data into standarized vectors, and all the way back.

londons_explore 1 days ago [-]
You can probably make jointly trained decoder to turn a vector back into a new document which most closely matches.

Would be cool to add together the vectors for harry potter and lord of the rings and then decode that into a new book about Frodo going to wizard school to collect the ring to help push Voldemort into mount doom.

Xx_crazy420_xX 23 hours ago [-]
klysm 1 days ago [-]
Isn’t that an auto encoder?
antirez 1 days ago [-]
It works with image embeddings too: https://youtu.be/r6TJfGUhv6s?si=_LC0d4Mwyw18c53B
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 16:30:41 GMT+0000 (Coordinated Universal Time) with Vercel.