they already use internally a POS tagger and a dependency parser.
Interesting. Where did you see that?
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.
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.
In my opinion, having a world model (for common sense) and situational awareness (e.g. through sensor fusion, or from prior conversational history, or using some externally supplied conditioning) would be far more important. Haha you basically want a general intelligence (AGI), I want it too! And not enough persons works on "architecting" such a thing. Opencog may interest you a lot then. But the reality is many other "simpler" tasks are needed to make this happen.
having a world model (for common sense) is an NLP task There are some interesting results https://github.com/sebastianruder/NLP-progress/blob/master/e... OpenAI does not work on this task sadly, at least for now.
You think adding POS tags would help it generate meaningful sentences? I would be clearly insufficient yet necessary. I believe they already use internally a POS tagger and a dependency parser.