MAJOR SCIENTIFIC ACHIEVEMENTS (PAST 5 YEARS)

Professor Yoko Yamakata received her Ph.D. from  the Graduate School of Informatics, Kyoto University, in 2007. She served as a lecturer and later as an associate professor at Kyoto University for six years starting in 2010. In 2015, she became a JSPS Research Fellow and conducted research as a visiting scholar at the University of Sussex in the UK, accompanied by her two sons. In 2019, she was appointed as an Associate Professor at the Graduate School of Information Science and Technology, the University of Tokyo, and in 2024, she became a Professor at the Information Technology Center of the University of Tokyo. Her specialty is in multimedia information processing, primarily focusing on deep learning techniques for text and images. She has a keen interest in AI-based technologies supporting food applications.

 A summary of the achieved results / project follows:

•           Text corpus on cooking recipe in both of English and Japanese

Prof. Shinsuke Mori, a professor of Kyoto University, and I have constructed a text corpus of cooking recipe. Since cooking recipe is considered as a procedural text, a recipe is able to be described as a flowgraph, that is formed as a directed acyclic graph (DAG), to represent its semantic structure. 208 Japanese recipes and more than 200 English recipes were already converted to this flowgraph format in manual and the number of the recipes in the corpora is increasing. Also we constructed a system for automatically extracting semantic structure from a recipe based on a machine leaning technique and the recipe corpora. This system is available for academic use and several Japanese research groups use them for various purpose including recipe analysis and recipe search and recommendation tasks.

§  Automatic tagging tool for recipe named entities 

§  Flow-graph converter for cooking recipe text

•           Smartphone food logging application “FoodLog” (iOS/Android)

A research member of Aizawa Lab, the university of Tokyo, Japan from September 2015 to date.

Aizawa Lab, which I am working with, have constructed a personal food logging system named “FoodLog”. Foodlog is a smartphone application for iOS/Android. When a user uploads a photo of his/her everyday food, the application automatically detects a region of each food item, recognizes it, and return the calorie for each food item based on the nutrition data. Our laboratory provides the service to anybody and now we obtained more than 4.7 million food records by more than 1000 active users. We also specialized this application for professional athletes as collaboration with Japan Institute of Sports Sciences (JISS) and for diabetic patients as a collaboration with Graduate School of Medicine and Faculty of Medicine, The University of Tokyo.

§  FoodLog on App Store

§  FoodLog on Google Play