Loading [MathJax]/extensions/MathZoom.js
  Edit on GitHub 

model = AutoAdapterModel.from_pretrained("xlm-roberta-base")
config = AdapterConfig.load("pfeiffer", non_linearity="relu", reduction_factor=16)
model.load_adapter("formality_classify/gyafc@martiansideofthemoon", config=config)

Description

This adapter has been trained on the English formality classification GYAFC dataset and tested with other language adapters (like hindi) for zero-shot transfer. Make sure to remove tokenization, lowercase and remove trailing punctuation for best results.

Properties

Pre-trained model
xlm-roberta-base
Adapter type
Task
Prediction Head
  Yes
Task
Formality Classification
Dataset
Grammarly's Yahoo Answers Formality Corpus (GYAFC)

Dependencies

This adapter should be used together with these dependencies to achieve best results:

Architecture

Name
pfeiffer
Non-linearity
relu
Reduction factor
16
{
  "ln_after": false,
  "ln_before": false,
  "mh_adapter": false,
  "output_adapter": true,
  "adapter_residual_before_ln": false,
  "non_linearity": "relu",
  "original_ln_after": true,
  "original_ln_before": true,
  "reduction_factor": 16,
  "residual_before_ln": true
}

Author

  Name
Kalpesh Krishna
  E-Mail
kalpesh@cs.umass.edu
  Web
https://martiansideofthemoon.github.io/
  GitHub
martiansideofthemoon
  Twitter
@kalpeshk2011

Versions

Identifier Comment Score Download
1 DEFAULT

Citations

Adapter
@inproceedings{krishna-etal-2020-reformulating,
    title = "Reformulating Unsupervised Style Transfer as Paraphrase Generation",
    author = "Krishna, Kalpesh  and
      Wieting, John  and
      Iyyer, Mohit",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.emnlp-main.55",
    doi = "10.18653/v1/2020.emnlp-main.55",
    pages = "737--762",
}
Architecture
@misc{pfeiffer2020adapterfusion,
  title={AdapterFusion: Non-Destructive Task Composition for Transfer Learning},
  author={Jonas Pfeiffer and Aishwarya Kamath and Andreas Rücklé and Kyunghyun Cho and Iryna Gurevych},
  year={2020},
  eprint={2005.00247},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
Task
@inproceedings{rao-tetreault-2018-dear,
    title = "Dear Sir or Madam, May {I} Introduce the {GYAFC} Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer",
    author = "Rao, Sudha  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/N18-1012",
    doi = "10.18653/v1/N18-1012",
    pages = "129--140",
}