-1
$\begingroup$

I am learning deep learning and I want to get into NLP. I have done LSTM, and now I am learning about vectorisation and transformers. Can you please tell me, which algorithm is more effective and accurate?

$\endgroup$
  • $\begingroup$ Welcome to DataScience StackExchange. Please make your question more clear. NLP is a very broad field of ML, and different models must be used for different tasks. GPT-3 and RoBERTa, specifically, have been created for different reasons. $\endgroup$ – Leevo Jul 30 at 19:56
1
$\begingroup$

They are meant for different purposes and they are hardly comparable.

RoBERTa is meant for text classification and tagging tasks. The idea is that you take a pretrained RoBERTa model and finetune it on your (potentially small) classification or tagging dataset. Some examples of tasks where RoBERTa is useful are sentiment classification, part-of-speech (POS) tagging and named entity recognition (NER).

GPT-3 is meant for text generation tasks. Its paradigm is very different, normally referred to as "priming". You basically take GPT-3, give it some text as context and let it generate more text. The context should give GPT-3 the "pattern" of what it must generate. You don't finetune it, just give it some example of acceptable text generation pattern and then let it generate more alike.

| improve this answer | |
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.