@inproceedings{Held_2023,
   title={TADA : Task Agnostic Dialect Adapters for English},
   url={http://dx.doi.org/10.18653/v1/2023.findings-acl.51},
   DOI={10.18653/v1/2023.findings-acl.51},
   booktitle={Findings of the Association for Computational Linguistics: ACL 2023},
   publisher={Association for Computational Linguistics},
   author={Held, William and Ziems, Caleb and Yang, Diyi},
   year={2023} }

Adapter WillHeld/pfadapter-bert-base-uncased-tada-adv for bert-base-uncased

An adapter for the bert-base-uncased model that was trained on the glue dataset.

This adapter was created for usage with the adapter-transformers library.

Usage

First, install adapter-transformers:

pip install -U adapter-transformers

Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

Now, the adapter can be loaded and activated like this:

from transformers import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("bert-base-uncased")
adapter_name = model.load_adapter("WillHeld/pfadapter-bert-base-uncased-tada-adv", source="hf", set_active=True)

Architecture & Training

Evaluation results

Citation