M
Margaret Mitchell
Researcher at Google
Publications - 109
Citations - 18187
Margaret Mitchell is an academic researcher from Google. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 42, co-authored 94 publications receiving 13094 citations. Previous affiliations of Margaret Mitchell include University of Aberdeen & Johns Hopkins University.
Papers
More filters
Patent
Discovery of semantic similarities between images and text
Jianfeng Gao,Xiaodong He,Saurabh Gupta,Geoffrey Zweig,Forrest Iandola,Li Deng,Hao Fang,Margaret Mitchell,John Platt,Rupesh Kumar Srivastava +9 more
TL;DR: In this paper, a deep multimodal similarity model was proposed to determine the relevance of the sentences based on similarity of text vectors generated for one or more sentences to an image vector generated for an image.
Proceedings ArticleDOI
Diversity and Inclusion Metrics in Subset Selection
Margaret Mitchell,Dylan Baker,Nyalleng Moorosi,Emily Denton,Ben Hutchinson,Alex Hanna,Timnit Gebru,Jamie Morgenstern +7 more
TL;DR: New metrics based on diversity and inclusion are introduced, which can be applied together, separately, and in tandem with additional fairness constraints, to create outputs that account for social power and access differentials.
Posted Content
Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias
TL;DR: A framework called image counterfactual sensitivity analysis is proposed, which is explored as a proof-of-concept in analyzing a smiling attribute classifier trained on faces of celebrities and demonstrates potential ways generative models can be leveraged for fine-grained analysis of bias and fairness.
Proceedings ArticleDOI
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
Hugo Laurenccon,Lucile Saulnier,Thomas Wang,Christopher Akiki,A. Villanova del Moral,Teven Le Scao,Leandro von Werra,Chenghao Mou,Eduardo G. Ponferrada,Huu Nguyen,Jorg Frohberg,Mario vSavsko,Quentin Lhoest,Angelina McMillan-Major,Gérard Dupont,Stella Biderman,Anna Rogers,Loubna Ben Allal,Francesco De Toni,Giada Pistilli,Olivier Nguyen,Somaieh Nikpoor,Maraim Masoud,Pierre Colombo,Javier Galiana de la Rosa,Paulo Villegas,Tristan Thrush,Shayne Longpre,Sebastian Nagel,Leon Weber,Manuel Sevilla Muñoz,Jian Zhou,Daniel van Strien,Zaid Alyafeai,Khalid Almubarak,Minh Chien Vu,Itziar Gonzalez-Dios,Aitor Soroa,Kyle Lo,Manan Dey,Pedro Javier Ortiz Suárez,Aaron Gokaslan,Shamik Bose,David Ifeoluwa Adelani,Long Phan,H. Tran,I. Yu,Suhas Pai,Jenny Chim,Violette Lepercq,Suzana Ilic,Margaret Mitchell,Sasha Luccioni,Yacine Jernite +53 more
TL;DR: The Responsible Open-science Open-collaboration Text Sources (ROOTS) corpus as mentioned in this paper is a 1.6TB dataset spanning 59 languages that was used to train the 176-billion-parameter BigScience Large Open science Open-access Multilingual (BLOOM) language model.
Posted Content
Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
Inioluwa Deborah Raji,Andrew Smart,Rebecca N. White,Margaret Mitchell,Timnit Gebru,Ben Hutchinson,Jamila Smith-Loud,Daniel Theron,Parker Barnes +8 more
TL;DR: In this article, the authors introduce a framework for algorithmic auditing that supports artificial intelligence system development end-to-end, to be applied throughout the internal organization development lifecycle, drawing on an organization's values or principles to assess the fit of decisions made throughout the process.