office: Doolan Hall 201B
email: mandy.korpusik@lmu.edu
News
Our ICASSP 2023 paper on multi-modal approaches to food classification was recently accepted! If you're interested in trying out the spoken diet tracking system I built during my PhD, feel free to download Coco Nutritionist from the Apple Store. Please let me know if you have any feedback!
About me
I graduated with my PhD from MIT in June, 2019 and I am now an Assistant Professor of Computer Science at Loyola Marymount University! My primary research interest is natural language processing (NLP), especially spoken language understanding and dialogue systems. For my PhD, I designed novel convolutional neural network models that perform semantic tagging and mapping of natural language meal descriptions to semantically similar USDA food database entries. I also demonstrated that asking followup clarification questions with deep reinforcement learning boosts food recall performance by narrowing down the search space. I showed that these neural convolutional models generalize to other tasks beyond nutrition, including semantic tagging of user queries in flight and movie booking domains, as well as dialogue state tracking for restaurant booking. I am interested in developing conversational agents for health that give personalized recommendations.
Multi-modal Food Classification in a Diet Tracking System with Spoken and Visual Inputs Shivani Gowda, Yifan (Rosetta) Hu, Mandy Korpusik
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), June 2023.
Nutrition System Demonstration Mandy korpusik, Rachael Naphtal, Nicole Schmidt, Scott Cyphers, James Glass
Spoken Language Technology Workshop (SLT), 2014.
April 2016, Service Award. Sidney Pacific Graduate Residence.
April 2015, Fellowship. National Defense Science and Engineering Graduate (NDSEG).
March 2015, Honorable Mention. National Science Foundation (NSF) Graduate Research Fellowship.
December 2014, Best Rated Poster Presentation Award: Demos. Spoken Language Technology Workshop (SLT), South Lake Tahoe.
Grants
August 2022, $50,000 Research Gift, eBay.
May 2022, Faith and Justic Research Grant, LMU.
December 2021, Capacity Building Grant, LMU, University Intercultural Council.
May 2021, Continuing Faculty Grant, LMU, Seaver College of Science and Engineering.
May 2021, Faith and Justice Course Development Grant, LMU.
May 2020, Faith and Justice Research Grant, LMU.
May 2020, Course Development Grant, LMU, Seaver College of Science and Engineering.
September 2019-Present, Rains Research Assistance Fund, LMU.
Patents
Korpusik, M. et al. A System and Method for Semantic Mapping of Natural Language Input to Database Entries via Convolutional Neural Networks. U.S. Patent 10817509, issued Oct. 27, 2020.