Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library
← Back to context

Comment by Solvency

2 years ago

Out of curiosity related to the word vectorization algorithm...why does one word not perform as well? Whats the cause/rationale?

1 comment

Solvency

Reply

julien040  2 years ago

It's pure speculation, but articles embeddings are computed using 512 tokens, which is roughly equivalent to 400 words. I think that using only one word does not allow the model to fully understand the context.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities