activebus/BERT-DK_laptop

BERT (post-)trained from review corpus to understand sentiment, options and various e-commence aspects . The original model is from BERT-base-uncased trained from Wikipedia+BookCorpus . The models are post-trained from Amazon Dataset and Yelp Datasets . The model weights are as simple as, e.g., importing AutoModel, AutoTokenizer, and loading the post-training weights are simple . Check our NAACL paper below: "BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis", "ReviewBERT," "Yelight", "jun", "month", "year", ",