Anthony Rios, assistant professor of information systems and cyber security in the Carlos Alvarez College of Business at UTSA, received a $550,000 National Science Foundation CAREER award to study natural language processing (NLP) within artificial intelligence. The five-year award is part of their Faculty Early Career Development Program. CAREER is the NSF’s most prestigious award designed to support early-career faculty who demonstrate potential to serve as academic role models in research and education.
Rios, who also serves as associate director of the Cyber Center for Security and Analytics at UTSA, will apply the grant funding to develop frameworks for practitioners to develop population-specific NLP models.
NLP is a branch of artificial intelligence that enables computers to understand and interpret human language. It is used in everyday applications such as Google Translate and Amazon Alexa. Most research focuses on generalizing or assuming a one-size-fits-all language framework. This proposal takes a different approach by developing models tailored to specific geographic populations, ethnic communities or groups.
Rios’s background and multidisciplinary research interests in NLP, machine learning and computational social science have equipped him with the expertise to lead this project. He received his first introduction to NLP during his computer science doctoral program at the University of Kentucky while working with his faculty advisor Ramakanth Kavuluru, an experienced NLP researcher. Rios was drawn to the subject due to its numerous applications and its impact on people and communication.
“NLP is about developing tools to understand language, but we do not have language without people,” explained Rios, who joined UTSA in 2018. “My specific focus is developing NLP tools for biomedical and social applications, which I feel can have a real-world impact and hopefully improve people’s lives.”
The grant-funded project involves three objectives. First, it will determine methods to detect correlations between community language and NLP model performance. The second objective includes developing a tool to assist community leaders with determining potential harms of specific NLP models and deciding whether it is relevant to the community. Lastly, the project aims to find processes and opportunities to improve NLP model performance.
“I’m interested in understanding how these models can impact people, and what biases exist within them,” Rios said. “There is a lot of hype surrounding NLP and artificial intelligence, but I think it’s important to avoid hype and to understand the potential harms caused by NLP models when they are deployed.”
The project will be managed through the Cyber Center for Security and Analytics, which is focused on finding innovative solutions to societal challenges. The Cyber Center cultivates academic, private and public sector collaborations to facilitate research and organizes research workforce development activities.
“The center provides a platform for researchers to connect and collaborate and matches potential collaborators with researchers based on needs and expertise,” Rios said. “This helps acquire more university funding for researchers and students.”