Stanford CS224N NLP with Deep Learning | 2023 | Lecture 11 - Natural Language Generation

[@uraskarg710]

Great lecture! Thanks!

[@robertokalinovskyy7347]

Great lecture!

[@mshonle]

Ah, interesting… I had wondered about the distinction between NLU and NLP and now it makes sense! Cheers!

[@420_gunna]

Great lecture! :)

[@mshonle]

Can using dropout during inference be another way to set the temperature and perform sampling? E.g., if training had a 10% dropout rate, why not apply a similar random dropout during inference? The neurons which get zeroed out could depend on some distribution, such as selecting neurons evenly or favoring the earlier layers or targeting attention heads at specific layers. One might expect the token distributions would be more varied than what beam search alone could find.

[@l501l501l]

Hi there, based on the schedule on your official course website, maybe this course should be lecture 10 and Prompting, Reinforcement Learning from Human Feedback by Jesse Mu) should be lecture 11?

[@banruo-tz7tx]

Yeah seems there is a mistake

[@yagneshm.bhadiyadra4359]

There is the mistake. Josh mentions this in lec 9.

[@p4r7h-v]

thanks!!

[@annawilson3824]

1:02:05

[@JQ0004]

The TA seems attends Ng`s class a lot. Seems to imitate "ok cool" a lot. 😀

[@yagneshbhadiyadra7938]

This is lec 10,not 11

[@yagneshm.bhadiyadra4359]

Please pin : This is lec 10, not 11