Search Results for author: Marion Bartl

Found 4 papers, 4 papers with code

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT’s Gender Bias

1 code implementation GeBNLP (COLING) 2020 Marion Bartl, Malvina Nissim, Albert Gatt

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.

counterfactual Word Embeddings

Inferring Gender: A Scalable Methodology for Gender Detection with Online Lexical Databases

1 code implementation LTEDI (ACL) 2022 Marion Bartl, Susan Leavy

This paper presents a new method for automatic detection of gendered terms in large-scale language datasets.

Towards Lexical Gender Inference: A Scalable Methodology using Online Databases

1 code implementation28 Jun 2022 Marion Bartl, Susan Leavy

and nouns with lexical gender ('mother', 'boyfriend', 'policewoman', etc.).

Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias

1 code implementation27 Oct 2020 Marion Bartl, Malvina Nissim, Albert Gatt

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems.

counterfactual Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.