Teaching Heritage to Artificial Intelligence Through Storytelling

Davar Ardalan
5 min readSep 23, 2021

--

The sun is setting over I-40 West as technologist Chamisa Edmo makes her way from Albuquerque to Phoenix to attend the American Indian Science and Engineering Society’s (AISES) conference. She’ll be joining us in presenting on the future of storytelling, artificial intelligence and indigenous knowledge.

Technologist Chamisa Edmo on her way to this week’s AISES conference in Phoenix

It’s been inspiring getting to know Chamisa in the past few years. A citizen of the Navajo Nation, Blackfeet and Shoshone-Bannock, Chamisa is an AI content developer who is passionate about the social justice side of data. Case in point: when we were planning our AISES workshop on training data, Chamisa sent me two powerful archival images. One of American Horse, an Oglala Lakota chief, educator and historian and the other featuring pupils at the Carlisle Indian Industrial School in Pennsylvania. Founded in 1879 by the US government, The Carlisle Indian Industrial School was part of a larger federally-funded effort to ethnically cleanse and culturally assimilate Native Americans.

Pupils at the Carlisle Indian Industrial School in Pennsylvania c. 1900 courtesy of Wikimedia Commons

As a Diné woman, Chamisa says she understands the traditional power of stories to preserve knowledge. She believes the age of AI can be no different. Machines also need to understand context, culture, and history. In the past year, Chamisa has been supporting our team at IVOW as we build the foundations of an Indigenous Knowledge Graph (IKG), a central repository of culturally-relevant narratives with tagged metadata related to food traditions.

At IVOW, we’re urging the AI community to help fix the bias in its systems by pausing to nurture accurate and diverse training data. In order to build and support intelligent AIs that are more culturally-aware, we need to provide a source of data to develop, train, and test. “With IKG, we want to inform people through culture,” Chamisa says.

IVOW’s Indigenous Knowledge Graph data

On Friday September 24, 2021, we’ll be leading a 3-hour workshop together with Chamisa and Tracy Monteith, Senior Software Engineer at Microsoft and a life-long member of AISES, on bias in data and the promise of storytelling to change this narrative. Tracy is the driving force and technical innovator behind the inclusion of the Cherokee Syllabary in Microsoft Windows and Office, the first tribal language with that distinction. His work continues with enhancing polymorphic-languages preservation and dissemination through the infusion of appropriate technology into indigenous circles. Tracy is also a proponent of expanding IVOW’s Indigenous Knowledge Graph and making it open-sourced.

The nature of humanity is to tell stories. Davar’s vision for IVOW and bringing cultural awareness to AI through stories resonates with me,” Monteith says. “In a way it is the most valuable part of society to listen to others so that we can make connections. All cultures tell stories in a wide array of ways. Just as fine art tells a story, so does graffiti. Oral traditions are the oldest form of communication that bonds us together. Much of the history of oral traditions is lost to time and as we structure and share our stories, the whole of humanity can contribute to the shared narrative.”

Tracy Monteith, Senior Software Engineer at Microsoft and a life-long member of AISES leading a hackathon

Reflecting on IKG, Tracy says we need a global-denominator of perspective that becomes more inclusive and valuable with each and every contribution. “The way tribal people think globally is muted, even though our first-voices are indistinguishable from the natural order of the earth,” Tracy says.

One of the founding technologists of the Indigenous Knowledge Graph together with us at IVOW is Victor Yarlott. A Ph.D. student in artificial intelligence and natural language processing at Florida International University, Victor previously was a Master’s student at MIT. As a descendant of the Crow Tribe, stories have always been a part of his life. Victor says he brought that part of himself to his work at MIT on broadening the cultural base of a story-understanding system and in his ongoing work at FIU in automatically detecting culturally-relevant narrative elements.

People bring the cultural part of themselves to every aspect of their life, Victor says, and whether interacting with or learning about them, intelligent systems need a resource like the Indigenous Knowledge Graph to become robust. “This is deeply important not only for systems that *interact* with other people, such as conversational agents like Siri, but also for systems *about* people, that analyse patterns in the data people produce,” Victor says.

Ardalan will present a clickable prototype of Pepo at AISES. Pepo is a fun mobile application that can discover, share, and preserve traditional recipes and sustainable food knowledge.

At our AISES workshop we will also be soft-launching IVOW’s food app Pepo, and sharing a demo of our conversational AI Sina. Throughout the millennia, family and cultural traditions have been passed down verbally through storytelling. With Pepo, this traditional knowledge is being transformed into AI-suitable datasets. ​Consumers and enterprises alike can now promote healthy eating habits and ensure that family and cultural values are not lost in our collective transition to a more digital and automated world.

With IKG, our next step is to generate funds to make the repository open-source. Artificial intelligence is reshaping society and changing how we live, learn, and work. We can all help AI to make all our stories count. Let’s do it.

Tech Entrepreneur and Executive Producer at National Geographic, Davar Ardalan is at the AISES conference in Phoenix, and will be presenting on Teaching Heritage to Artificial Intelligence Through Storytelling on Friday September 24.

Davar Ardalan is the founder and chief storytelling officer at IVOW — intelligent voices of wisdom. Realizing that there is a gaping hole in AI algorithms that will define our future stories, Davar created IVOW, to champion culturally conscious data strategies across multiple industries from academia to development and enterprise.

Ardalan, who is also an Executive Producer at National Geographic, served as co-chair of the Cultural Heritage and AI track at ITU’s AI For Good in 2020. Prior to this, she was Deputy Director of the White House Presidential Innovation Fellowship Program in Washington D.C. and before that a long-time journalist at NPR News, where she was Senior Producer of the Identity and Culture Unit.

INDIGENOUS KNOWLEDGE GRAPH TEAM at IVOW / Davar Ardalan, Founder and Storyteller in Chief; Kee Malesky, Director of Editorial Content; Karim Ardalan, CTO; Nikki McLay Creative Director; Nisa McCoy, Head of Product, Miroslav Milovanovic, AI Scientist. In collaboration with Wolfgang Victor Yarlott, AI Researcher Florida International University of the Crow Tribe of Montana; Tracy Monteith, Senior Software Engineer at Microsoft of the Eastern Band Cherokee; Technologist Chamisa Edmo of the Navajo Nation; Alva Lim, Co-Founder and Director of Agora Food Studio by the Timor-Leste Food Lab.

--

--

Davar Ardalan

Founder TulipAI. National Geographic, NPR News, SecondMuse, White House PIF Alum.