Task Adapters

MultiNLI

Multi-Genre Natural Language Inference is a large-scale, crowdsourced entailment classification task. Given a pair of sentences, the goal is to predict whether the second sentence is an entailment, contradiction, or neutral with respect to the first one.

nli/multinli@ukp bert-base-uncased

1 version Architecture: houlsby

Adapter in Houlsby architecture trained on the MultiNLI task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.

nli/multinli@ukp roberta-large

1 version Architecture: pfeiffer

Adapter (with head) trained using the `run_glue.py` script with an extension that retains the best checkpoint (out of 10 epochs).

nli/multinli@ukp roberta-base

1 version Architecture: pfeiffer

Pfeiffer Adapter trained on Multi-NLI.

nli/multinli@ukp bert-base-uncased

1 version Architecture: pfeiffer

Adapter in Pfeiffer architecture trained on the MultiMLI task for 20 epochs with early stopping and a learning rate of 1e-4. See https://arxiv.org/pdf/2007.07779.pdf.