Workshop: Muslims in ML

Marzyeh Ghassemi, Mohammad Norouzi, Shakir Mohamed, Aya Salama, Tasmie Sarker

2020-12-08T07:30:00-08:00 - 2020-12-08T11:00:00-08:00
Abstract: Muslims In ML (MusIML) is an affinity workshop for the NeurIPS community.

We focus on both the potential for advancement and harm to Muslims and those in Muslim-majority countries who religiously identify, culturally associate, or are classified by proximity, as “Muslim”.

The workshop will run on Tuesday, December 8, 2020 from 10:30AM - 1:30PM EST.

We will feature a combination of pre-recorded and live talks, followed by a panel discussion with authors on the intersection of policy, technology, and Muslim communities.



Chat is not available.


2020-12-08T07:30:00-08:00 - 2020-12-08T07:35:00-08:00
Marzyeh Ghassemi
2020-12-08T07:35:00-08:00 - 2020-12-08T08:00:00-08:00
Investigating Anti-Muslim Bias in GPT-3 through Words, Images, & Stories
Abubakar Abid
2020-12-08T08:00:00-08:00 - 2020-12-08T08:01:00-08:00
Intro: Anver Emon
2020-12-08T08:02:00-08:00 - 2020-12-08T08:25:00-08:00
Taking from the Hands that Give: CRA audits of Muslim-led Charities
Anver Emon
2020-12-08T08:25:00-08:00 - 2020-12-08T08:26:00-08:00
Intro: Ted Pedersen
2020-12-08T08:26:00-08:00 - 2020-12-08T08:50:00-08:00
Automatically Identifying Islamophobia in Social Media
Ted Pedersen
Social media continues to grow in its scope, importance, and toxicity. Hate speech is ever-present in today’s social media, and causes or contributes to dangerous situations in the real world for those it targets. Anti-Muslim bias and hatred has escalated in both public life and social media in recent years. This talk will overview a new and ongoing project in identifying Islamophobia in social media using techniques from Natural Language Processing. I will describe our methods of data collection and annotation, and discuss some of the challenges we have encountered thus far. In addition I’ll describe some of the pitfalls that exist for any effort attempting to identify hate speech (automatically or not).
2020-12-08T08:50:00-08:00 - 2020-12-08T08:51:00-08:00
Intro: Darren Byler
2020-12-08T08:51:00-08:00 - 2020-12-08T09:15:00-08:00
The Digital Enclosure of Turkic Muslims in Northwest China
Darren Byler
In this short talk I use the conceptual framing of a digital enclosure to consider the way Uyghur and Kazakh societies in Northwest China have been enveloped by a surveillance system over the past decade. I show how novel enclosures are produced and, in turn, construct new frontiers in capital accumulation and state power. The Turkic Muslim digital enclosure system began with the construction of 3-G cellular wireless networks which provided Uyghurs and Kazakhs with interactive smart-phone enabled capabilities across time and space. But over time state authorities paid private technology companies to build a data-intensive system with a wide range of spatial scales and information analytics that came to center on "Muslim" social media assessment and ethno-racialized face recognition technology. This complex matrix of overlaid enclosures assessed and controlled the movements and behavior of Muslims in increasingly intimate ways, resulting in mass detentions in "reeducation" camps. What makes the case in Northwest China unique beyond its scale and cruelty, is that in this context rather than banishing targeted populations solely to human warehousing spaces such as peripheral ghettos, camps or prisons, the digital enclosure works to explicitly “reeducate” the population as industrial workers and implement a forced labor regime.
2020-12-08T09:15:00-08:00 - 2020-12-08T09:16:00-08:00
Intro: Nayel Shafei
2020-12-08T09:16:00-08:00 - 2020-12-08T09:30:00-08:00
Creating Multilingual Corpora for Arabic Characterset
Nayel Shafei
2020-12-08T09:30:00-08:00 - 2020-12-08T09:45:00-08:00
Data Paucity and Low Resource Scenarios: Challenges and Opportunities
Mona Diab
In an era unstructured data abundance, you would think that we have solved our data requirements for building robust systems for language processing. However, this is not the case if we think on a global scale with over 7000 languages where only a handful have digital resources. Moreover, systems at scale with good performance typically require annotated resources.The existence of a handful of resources in a some languages is a reflection of the digital disparity in various societies leading to inadvertent biases in systems. In this talk I will show some solutions for low resource scenarios, both cross domain and genres as well as cross lingually.
2020-12-08T09:45:00-08:00 - 2020-12-08T10:00:00-08:00
NLU Meets Islamic Religious Phrases: Highlighting the Challenges
Samhaa R. El-Beltagy
2020-12-08T10:00:00-08:00 - 2020-12-08T10:30:00-08:00
Policy Panel
Roya Pakzad, Dia Kayyali, Marzyeh Ghassemi, Shakir Mohamed, Mohammad Norouzi, Ted Pedersen, Anver Emon, Abubakar Abid, Darren Byler, Samhaa R. El-Beltagy, Nayel Shafei, Mona Diab
In this short talk, Roya Pakzad will speak about her current project entitled "Nuanced Counter-Narratives of Being Muslim Online." The goal of this project is to gain a deeper understanding of how marginalized groups create counter-narratives, who amplifies them, how sustainable they are, and how their impact differs. By providing various examples, she will also touch on how technology companies' business models and their third-party relationships impact Muslims and people from Muslim-majority countries. The talk will conclude with recommendations for design and policy interventions. The workshop will conclude with a discussion with authors and organizers.