Mandy Korpusik

Graduate Student

Mandy Korpusik received her B.S. in Electrical and Computer Engineering from Franklin W. Olin College of Engineering in May, 2013 and completed her S.M. at MIT in June, 2015. She is currently pursuing her Ph.D. in the Spoken Language Systems group. Her primary research interests include natural language processing and spoken language understanding, and she has previously worked on user intent detection, semantic tagging, and predicting user purchase behavior. Currently, she is working with Dr. Jim Glass on a nutrition dialogue system that uses convolutional neural networks to map between natural language meal descriptions to USDA food database entries. She is also interested in encoder-decoder models for conversational agents, caption generation, and translation.




Voice-controlled calorie counter

For people struggling with obesity, logging calorie counts and other nutritional information at every meal is a proven way to lose weight. The technique does require consistency and accuracy, however, and when it fails, it’s usually because people don't have the time to find and record all the information they need.A few years ago, a team of nutritionists from Tufts University who had been experimenting with mobile-phone apps for recording caloric intake approached members of the Spoken Language Systems Group at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), with the idea of a spoken-language application that would make meal logging even easier.