Intelligent Wikipedia
Berners-Lee's compelling vision of a Semantic Web is hindered by a chicken-and-egg problem, which can be best solved by a bootstrapping method, creating enough structured data to motivate the development of applications. However, automatic information extraction systems produce errors and are not tolerated by users, whereas user contributions incentives and management to control vandalism. We therefore propose systems that tightly integrate human and machine feedback: information extraction techniques generate candidate facts, and users correct errors, improving training data and enabling a virtuous cycle.
People
Publications
- Learning 5000 Relational Extractors (2010)
- Machine Reading: from Wikipedia to the Web (2010)
- Open Information Extraction using Wikipedia (2010)
- Temporal Information Extraction (2010)
- Machine Reading at the University of Washington (2010)
- Amplifying Community Content Creation with Mixed Initiative Information Extraction (2009)
- Information Extraction from Wikipedia: Moving Down the long Tail (2008)
- Automatically Refining the Wikipedia Infobox Ontology (2008)
- Autonomously Semantifying Wikipedia (2007)
Research Groups
Last changed Thu, 2012-11-29 14:50

cs.