What Do Users Want? Using Semantics to Predict User Intents at Scale
Over the years search paradigm has shifted from document retrieval to deeper user intent understanding. Today’s users are no longer satisfied with seeing a list of relevant documents, instead they want to complete tasks and take actions on them. The question I will address in this talk is how to build an automated user intent understanding system, where given a query like "Mia" the user sees relevant and personalized recommendations such as "buy latest album of the singer”, or "check-in flight to Miami". I will begin by introducing the task and the main challenges with semantic understanding. Then, I will describe categorization and structured prediction algorithms for entity detection and intent prediction. Finally, I will highlight results and findings for user intent prediction from shopping, movies, restaurant and sport domains.
Dr. Zornitsa Kozareva is a Manager at Amazon leading the Natural Language Processing group. Before that she was a Senior Manager at Yahoo! leading the Query Processing group that powers Mobile Search and Advertisement. From 2009 to 2014, Dr. Kozareva was a Research Assistant Professor at the University of Southern California and a Research Scientist at the Information Sciences Institute. Her interests lie in Web-based knowledge acquisition, semantics, ontology population, multilingual information extraction and sentiment analysis. Dr. Kozareva regularly serves as Area Chair and PC of top tier NLP conferences. She has organized four SemEval scientific challenges and has published over 60 research papers. Dr. Kozareva is a recipient of the John Atanasoff Award given by the President of Republic of Bulgaria in 2016 for her contributions and impact in science, education and industry; the Yahoo! Labs Excellence Award in 2014 and the RANLP Young Scientist Award in 2011.