Transformers

GPT is a Transformer-based architecture and training procedure for natural language processing tasks. Training follows a two-stage procedure. First, a language modeling objective is used on the unlabeled data to learn the initial parameters of a neural network model. Subsequently, these parameters are adapted to a target task using the corresponding supervised objective.

Source: Improving Language Understanding by Generative Pre-Training

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Language Modelling 94 11.66%
Large Language Model 49 6.08%
Question Answering 36 4.47%
Text Generation 26 3.23%
Prompt Engineering 24 2.98%
Decision Making 21 2.61%
In-Context Learning 21 2.61%
Sentence 20 2.48%
Retrieval 20 2.48%

Categories