Task Adapters

IMDb

MDB dataset having 50K movie reviews for natural language processing or Text analytics. This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. We provide a set of 25,000 highly polar movie reviews for training and 25,000 for testing. So, predict the number of positive and negative reviews using either classification or deep learning algorithms.

sentiment/imdb@ukp bert-base-uncased

1 version Architecture: pfeiffer Head:

Pfeiffer Adapter trained on the IMDb dataset.

sentiment/imdb@ukp roberta-base

1 version Architecture: pfeiffer Head:

Pfeiffer Adapter trained on the IMDb dataset.

sentiment/imdb@ukp distilbert-base-uncased

1 version Architecture: pfeiffer Head:

Adapter for distilbert-base-uncased in Pfeiffer architecture trained on the IMDB dataset for 15 epochs with early stopping and a learning rate of 1e-4.