Text Analytics Toolbox Model for BERT-Base Network

Pretrained BERT-Base Network for MATLAB

BERT-Base is a pretrained language model based on Deep Learning Transformer architecture that can be used for a wide variety of Natural Language Processing (NLP) tasks. This model has 12 self-attention layers and a hidden size of 768.

To load a BERT-Base model, run the following code:

[net, tokenizer] = bert(Model="base");