Lucy Vasserman
YOU?
Author Swipe
View article: Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation
Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation Open
Machine learning models are commonly used to detect toxicity in online conversations. These models are trained on datasets annotated by human raters. We explore how raters' self-described identities impact how they annotate toxicity in onl…
View article: A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers Open
On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area. Mor…
View article: Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation
Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation Open
Machine learning models are commonly used to detect toxicity in online conversations. These models are trained on datasets annotated by human raters. We explore how raters' self-described identities impact how they annotate toxicity in onl…
View article: ”You have to prove the threat is real”: Understanding the needs of Female Journalists and Activists to Document and Report Online Harassment
”You have to prove the threat is real”: Understanding the needs of Female Journalists and Activists to Document and Report Online Harassment Open
Online harassment is a major societal challenge that impacts multiple\ncommunities. Some members of community, like female journalists and activists,\nbear significantly higher impacts since their profession requires easy\naccessibility, t…
View article: A New Generation of Perspective API: Efficient Multilingual Character-level Transformers
A New Generation of Perspective API: Efficient Multilingual Character-level Transformers Open
On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area. Mor…
View article: Lost in Distillation: A Case Study in Toxicity Modeling
Lost in Distillation: A Case Study in Toxicity Modeling Open
In an era of increasingly large pre-trained language models, knowledge distillation is a powerful tool for transferring information from a large model to a smaller one. In particular, distillation is of tremendous benefit when it comes to …
View article: Measuring and Improving Model-Moderator Collaboration using Uncertainty\n Estimation
Measuring and Improving Model-Moderator Collaboration using Uncertainty\n Estimation Open
Content moderation is often performed by a collaboration between humans and\nmachine learning models. However, it is not well understood how to design the\ncollaborative process so as to maximize the combined moderator-model system\nperfor…
View article: Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation
Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation Open
Content moderation is often performed by a collaboration between humans and machine learning models. However, it is not well understood how to design the collaborative process so as to maximize the combined moderator-model system performan…
View article: Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification Open
Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of t…
View article: Nuanced Metrics for Measuring Unintended Bias with Real Data for Text\n Classification
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text\n Classification Open
Unintended bias in Machine Learning can manifest as systemic differences in\nperformance for different demographic groups, potentially compounding existing\nchallenges to fairness in society at large. In this paper, we introduce a suite\no…
View article: Limitations of Pinned AUC for Measuring Unintended Bias
Limitations of Pinned AUC for Measuring Unintended Bias Open
This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric. However, as we hig…
View article: Measuring and Mitigating Unintended Bias in Text Classification
Measuring and Mitigating Unintended Bias in Text Classification Open
We introduce and illustrate a new approach to measuring and mitigating unintended bias in machine learning models. Our definition of unintended bias is parameterized by a test set and a subset of input features. We illustrate how this can …