Re:GPT-2: 6-Month Follow-Up
by The_rationalist on Tuesday August 20, 2019 @06:15PM
(#20752751)
Well it was just a belief.
I may be wrong.
I asked them by curiosity https://github.com/openai/gpt-2/issues/168
So we will know.
[ Parent
| on HN ]
How do you think it could be used there? A separate model just for providing tags, or the same model but trained to predict tags as well?
Re:GPT-2: 6-Month Follow-Up
by The_rationalist on Wednesday August 21, 2019 @09:48AM
(#20757087)
I was imagining using a separate model just for providing tags as they are very accurate. It would theoretically give gpt-2 useful data.
GPT-2 has not (yet) been trained to predict POS tags to my knowledge, nor BERT, or ernie 2 or xlnet has, but I think they have great potential to improve POS accuracy.