Harvesting, Searching, and Ranking Knowledge from the Web

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=-Cnc_QG6_Fs


Duration: 1:06:26
528 views
6

There is a trend to advance the functionality of search engines to a more expressive semantic level. This is enabled by employing large-scale information extraction of entities and relationships from semistructured as well as natural-language Web sources. In addition, harnessing Semantic-Web-style ontologies and reaching into Deep-Web sources can contribute towards a grand vision of turning the Web into a comprehensive knowledge base that can be efficiently searched with high precision. This talk presents ongoing research at the Max-Planck Institute for Informatics towards this objective, centered around the YAGO knowledge base and the NAGA search engine. YAGO is a large collection of entities and relational facts that are harvested from Wikipedia and WordNet with high accuracy and reconciled into a consistent RDF-style semantic graph. NAGA provides graph-template-based search over this data, with powerful ranking capabilities based on a statistical language model for graphs. Advanced queries and the need for ranking approximate matches pose efficiency and scalability challenges that are addressed by algorithmic and indexing techniques. This is joint work with Georgiana Ifrim, Gjergji Kasneci, Maya Ramanath, and Fabian Suchanek.



Other Videos By Microsoft Research


2016-09-06Snoop: What Your Stuff Says About You
2016-09-06Overview of Ricoh's California Research Center
2016-09-06Mirroring People: the New Science of How We Connect with Others
2016-09-06Discovering Properties about Arrays in Simple Programs
2016-09-06Iconic Scene Graphs and Iconic Summaries for Internet Photo Collections
2016-09-06The Time-Triggered Architecture
2016-09-06Modeling Deformable Surfaces from Single Videos
2016-09-06Hardware Features can Undermine Software Security
2016-09-06C to FPGA Compilation and Domain-Specific Computing
2016-09-06Helping Moore's Law: Architectural Techniques to Address Parameter Variation
2016-09-06Harvesting, Searching, and Ranking Knowledge from the Web
2016-09-06Precision-Integrated Scalable Monitoring
2016-09-06Toward an Open Analytics Environment
2016-09-06In-Car Speech User Interfaces and their Effects on Driving Performance
2016-09-06Microcosm: E. coli and the New Science of Life
2016-09-06Dependable and Sustainable Cyber-Physical Computing - An Overview of IMPACT Lab's Research
2016-09-06General Theorem Proving for Satisfiability Modulo Theories: An Overview
2016-09-06Real-Time Concurrent Garbage Collection
2016-09-06Virtual Earth Summit - Session 2
2016-09-06Concept Lexicon Construction and Affective Analysis: From Photos to MTV
2016-09-06Cloud Computing for e-Science


Tags:
microsoft research