paper-with-me

Papers

Measuring and Reducing Gendered Correlations in Pre-trained Models

2020-10-12 · Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Ed Chi, Slav Petrov

Pre-trained models have revolutionized natural language understanding. However, researchers have found they can encode artifacts undesired in many applications, such as professions correlating with one gender more than another. We explore such gendered correlations as a case study for how to address unintended correlations in pre-trained models. We define metrics and reveal that it is possible for models with similar accuracy to encode correlations at very different rates. We show how measured correlations can be reduced with general-purpose techniques, and highlight the trade offs different strategies have. With these results, we make recommendations for training robust models: (1) carefully evaluate unintended correlations, (2) be mindful of seemingly innocuous configuration differences, and (3) focus on general mitigations.

📄 PDF Abstract BibTeX arXiv:2010.06032

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Gendered Language in Resumes

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Despite growing concerns around gender bias in NLP models used in algorithmic hiring, there is little empirical work studying the extent and nature of gendered language in resumes. Using a corpus of 709k resumes from IT …

Investigating Cross-Linguistic Gender Bias in Hindi-English Across Domains

2021-11-22 · Somya Khosla

Measuring, evaluating and reducing Gender Bias has come to the forefront with newer and improved language embeddings being released every few months. But could this bias vary from domain to domain? We see a lot of work t…

Translation

Gendered Language in Resumes and its Implications for Algorithmic Bias in Hiring

2022-07-01 · NAACL (GeBNLP) 2022 7 · Prasanna Parasurama, João Sedoc

Despite growing concerns around gender bias in NLP models used in algorithmic hiring, there is little empirical work studying the extent and nature of gendered language in resumes.Using a corpus of 709k resumes from IT f…

Fairness

Measuring Gender Bias in Word Embeddings of Gendered Languages Requires Disentangling Grammatical Gender Signals

2022-06-03 · Shiva Omrani Sabbaghi, Aylin Caliskan

Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages s…

Word Embeddings

Degendering Resumes for Fair Algorithmic Resume Screening

2021-12-16 · Prasanna Parasurama, João Sedoc

We investigate whether it is feasible to remove gendered information from resumes to mitigate potential bias in algorithmic resume screening. Using a corpus of 709k resumes from IT firms, we first train a series of model…

Fairness