Hacker News new | ask | show | jobs
by TillE 1286 days ago
I'm not entirely clear on what ActivityNet is (one of the primary sources for HellaSwag), but it looks like amateurish descriptions of videos, like you would write for audio descriptions for the blind, except written very badly.

I'm guessing it's just Mechanical Turk content which wasn't even spellchecked.

1 comments

Agreed, but I am concerned over the chance that lots of these models are used in critical scenarios without much validation of the data set.