no code implementations • NAACL (HCINLP) 2022 • Angelina McMillan-Major, Amandalynne Paullada, Yacine Jernite
With the growth of Automatic Content Moderation (ACM) on widely used social media platforms, transparency into the design of moderation technology and policy is necessary for online communities to advocate for themselves when harms occur. In this work, we describe a suite of interactive modules to support the exploration of various aspects of this technology, and particularly of those components that rely on English models and datasets for hate speech detection, a subtask within ACM.
1 code implementation • LTEDI (ACL) 2022 • Courtney Mansfield, Amandalynne Paullada, Kristen Howell
PII masking is commonly used to redact personal information such as names, addresses, and phone numbers from text data.
no code implementations • 26 Nov 2021 • Inioluwa Deborah Raji, Emily M. Bender, Amandalynne Paullada, Emily Denton, Alex Hanna
There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks.
no code implementations • Findings (EMNLP) 2021 • Naomi Tachikawa Shapiro, Amandalynne Paullada, Shane Steinert-Threlkeld
We introduce a multilabel probing task to assess the morphosyntactic representations of word embeddings from multilingual language models.
no code implementations • 9 Dec 2020 • Amandalynne Paullada, Inioluwa Deborah Raji, Emily M. Bender, Emily Denton, Alex Hanna
Datasets have played a foundational role in the advancement of machine learning research.