‹ BackHN Continuity

Thread

I built non-autoregressive decision models with RL a year ago

1363 points · 319 comments · nandakishor_ml

  1. nfcampos · · focus · HN ↗
    Isn’t this post comparing zero shot Jev to fine tunes of this model for each of the datasets it is tested on? If so seems like fairly impressive results for Jev
    1. fra · · focus · HN ↗
      Most valuable comment here. You can fine tune BERT to perform really well on classification tasks. What's exciting about Jev is that it generalizes. Laya does not!
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.