Shadowgraph
TrendingAbout
Sign in

princeton-nlp/mabel-bert-base-uncased

Model

Model Card for mabel-bert-base-uncased

0

4 commits

1 linked in READMEs

updated Nov 18, 2022

See the code

README

Model Card for mabel-bert-base-uncased

Model Description

This is the model for MABEL, as described in our paper, "MABEL: Attenuating Gender Bias using Textual Entailment Data". MABEL is trained from an underlying bert-base-uncased backbone, and demonstrates a good bias-performance tradeoff across a suite of intrinsic and extrinsic bias metrics.

bert
endpoints_compatible
fill-mask
gender-bias
pytorch
transformers

Similar repos

princeton-nlp/MABEL

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data"…

37

google-bert/bert-base-uncased

Model

BERT base model (uncased)

3,381

princeton-nlp/mabel-bert-large-uncased

Model

0

google-bert/bert-base-cased

Model

BERT base model (cased)

377

cl-nagoya/defsent-bert-base-uncased-mean

Model

0

cl-nagoya/defsent-bert-base-uncased-max

Model

0

cl-nagoya/defsent-bert-base-uncased-cls

Model

0

huggingface/bert-base-cased-wikitext2

Model

1

Linked in READMEs

princeton-nlp/MABEL

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data"…

37

README badge

princeton-nlp/mabel-bert-base-uncased

Model

Model Card for mabel-bert-base-uncased

0

4 commits

1 linked in READMEs

updated Nov 18, 2022

See the code

README

Model Card for mabel-bert-base-uncased

Model Description

This is the model for MABEL, as described in our paper, "MABEL: Attenuating Gender Bias using Textual Entailment Data". MABEL is trained from an underlying bert-base-uncased backbone, and demonstrates a good bias-performance tradeoff across a suite of intrinsic and extrinsic bias metrics.

bert
endpoints_compatible
fill-mask
gender-bias
pytorch
transformers

Similar repos

princeton-nlp/MABEL

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data"…

37

google-bert/bert-base-uncased

Model

BERT base model (uncased)

3,381

princeton-nlp/mabel-bert-large-uncased

Model

0

google-bert/bert-base-cased

Model

BERT base model (cased)

377

cl-nagoya/defsent-bert-base-uncased-mean

Model

0

cl-nagoya/defsent-bert-base-uncased-max

Model

0

cl-nagoya/defsent-bert-base-uncased-cls

Model

0

huggingface/bert-base-cased-wikitext2

Model

1

Linked in READMEs

princeton-nlp/MABEL

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data"…

37

README badge