Entities, Graphs, and Crowdsourcing for better Web Search

The Faculty of Informatics is pleased to announce a seminar given by Gianluca Demartini

DATE: Monday, June 10th, 2013
PLACE: USI Lugano Campus, room SI-008, Informatics building (Via G. Buffi 13)
TIME: 10.30

ABSTRACT:
Over the last years we have observed an evolution of Search Engine Result Pages which are now including more and more results from verticals like pictures, news, videos, factual data, and more. This has become possible also thanks to a deeper understanding of user queries and of Web content: entities are being extracted out of Web pages and uniquely identified. This enables entity-centric query answering.
In this talk I will overview different research challenges that needs to be tackled to enable such novel search result pages. First, I will talk about entity linking and disambiguation using crowdsourcing and a graph of linked entities as background corpus. Next, I will show how such identified entities can be effectively ranked as answer to a user keyword query by combining both inverted indices and a graph structures. Finally, I will describe how keyword query understanding can be crowdsourced to build search engines that can answer rare complex queries.

BIO:
Dr. Gianluca Demartini is a post-doctoral researcher at the Department of Computer Science of the University of Fribourg, Switzerland. Previously, he was visiting researcher at UC Berkeley, junior researcher at the L3S Research Center, and intern at Yahoo! Research.
His research interests include Web Information Retrieval, Semantic Web, and Crowdsourcing. His Ph.D. work focused on Entity Retrieval. He has published more than 40 peer-reviewed scientific publications and given tutorials about Entity Search and Crowdsourcing at research conferences.

HOST: Prof. Fabio Crestani