758 citations · 1.8k across the 31 of their papers we have counts for
34 papers
Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desiderata
Amy K. Heger, Liz B. Marquis, Mihaela Vorvoreanu +2
Data is central to the development and evaluation of machine learning (ML) models. However, the use of problematic or inappropriate datasets can result in harms when the resulting…
REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research
Jessie J. Smith, Saleema Amershi, Solon Barocas +2
Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible. D…
Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support
Michael Madaio, Lisa Egede, Hariharan Subramonyam +2
Various tools and practices have been developed to support practitioners in identifying, assessing, and mitigating fairness-related harms caused by AI systems. However, prior resea…
Doubly Non-Central Beta Matrix Factorization for DNA Methylation Data
Aaron Schein, Anjali Nagulpally, Hanna Wallach +1
We present a new non-negative matrix factorization model for bounded-support data based on the doubly non-central beta (DNCB) distribution, a generalization of the beta dis…
From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence
David Alvarez-Melis, Harmanpreet Kaur, Hal Daumé +2
We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on huma…
Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs
Solon Barocas, Anhong Guo, Ece Kamar +5
Disaggregated evaluations of AI systems, in which system performance is assessed and reported separately for different groups of people, are conceptually simple. However, their des…
Language (Technology) is Power: A Critical Survey of "Bias" in NLP
Su Lin Blodgett, Solon Barocas, Hal Daumé +1
We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyz…
On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs
Adina Williams, Ryan Cotterell, Lawrence Wolf-Sonkin +2
We use large-scale corpora in six different gendered languages, along with tools from NLP and information theory, to test whether there is a relationship between the grammatical ge…
Measurement and Fairness
Abigail Z. Jacobs, Hanna Wallach
We propose measurement modeling from the quantitative social sciences as a framework for understanding fairness in computational systems. Computational systems often involve unobse…
Weight of Evidence as a Basis for Human-Oriented Explanations
David Alvarez-Melis, Hal Daumé, Jennifer Wortman Vaughan +1
Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via , w…
Quantifying the Semantic Core of Gender Systems
Adina Williams, Ryan Cotterell, Lawrence Wolf-Sonkin +2
Many of the world's languages employ grammatical gender on the lexeme. For example, in Spanish, the word for 'house' (casa) is feminine, whereas the word for 'paper' (papel) is mas…
Poisson-Randomized Gamma Dynamical Systems
Aaron Schein, Scott W. Linderman, Mingyuan Zhou +2
This paper presents the Poisson-randomized gamma dynamical system (PRGDS), a model for sequentially observed count tensors that encodes a strong inductive bias toward sparsity and…
Toward Fairness in AI for People with Disabilities: A Research Roadmap
Anhong Guo, Ece Kamar, Jennifer Wortman Vaughan +2
AI technologies have the potential to dramatically impact the lives of people with disabilities (PWD). Indeed, improving the lives of PWD is a motivator for many state-of-the-art A…
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling
Alexander Hoyle, Wolf-Sonkin, Hanna Wallach +2
Studying the ways in which language is gendered has long been an area of interest in sociolinguistics. Studies have explored, for example, the speech of male and female characters…
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach +1
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender ste…
What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
Alexey Romanov, Maria De-Arteaga, Hanna Wallach +7
There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race,…
Combining Sentiment Lexica with a Multi-View Variational Autoencoder
Alexander Hoyle, Lawrence Wolf-Sonkin, Hanna Wallach +2
When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, ann…
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
Maria De-Arteaga, Alexey Romanov, Hanna Wallach +6
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the…
Improving fairness in machine learning systems: What do industry practitioners need?
Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé +2
The potential for machine learning (ML) systems to amplify social inequities and unfairness is receiving increasing popular and academic attention. A surge of recent work has focus…
The Hyperedge Event Model
Bomin Kim, Aaron Schein, Bruce A. Desmarais +1
We introduce the hyperedge event model (HEM)---a generative model for events that can be represented as directed edges with one sender and one or more receivers or one receiver and…
Datasheets for Datasets
Timnit Gebru, Jamie Morgenstern, Briana Vecchione +4
The machine learning community currently has no standardized process for documenting datasets, which can lead to severe consequences in high-stakes domains. To address this gap, we…
Locally Private Bayesian Inference for Count Models
Aaron Schein, Zhiwei Steven Wu, Alexandra Schofield +2
We present a general method for privacy-preserving Bayesian inference in Poisson factorization, a broad class of models that includes some of the most widely used models in the soc…
A Reductions Approach to Fair Classification
Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík +2
We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach enco…
Manipulating and Measuring Model Interpretability
Forough Poursabzi-Sangdeh, Daniel G. Goldstein, Jake M. Hofman +2
With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Altho…