Presented at: 10th International Semantic Web Conference (ISWC2011)
by Alfio Massimiliano Gliozzo, Aditya Kalyanpur, Chris Welty
Watson (http://ibmwatson.com) is an open-domain natural language question answering system that answers questions with precision and confidence rivaling the best human experts at the task, and that emerged victorious in a widely viewed public challenge on the American TV Quiz Show, Jeopardy!. Semantic Web Technology, enhanced by a massive use of open linked data, plays a crucial role in Watson. For example, linked data such as DBpedia and Geonames and triple stores such as Sesame have been used to generate candidate answers and to score them under multiple points of view such as type coercion and geographic proximity. In addition, the connection between linked data and natural language text offered by Wikipedia has been very useful to generate open domain training data for relation detection and entity recognition systems, substantially improving the NLP capabilities of the system and therefore allowing the development of a truly open domain QA system. This tutorial is focus on the Semantic Web Technology adopted by Watson and on how it fits in the general Deep QA architecture. The tutorial is structured in two parts, the first focusing on the open-domain QA challenge and the Watson architecture, the second focused on the use of semantic web technology and linked open data in Watson. Tutorial webpage: http://iswc2011.semanticweb.org/tutorials/semantic-web-technology-in-watson/
Semantic Web Technology in Watson was presented at this event.
Resource URI on the dog food server: http://data.semanticweb.org/conference/iswc/2011/paper/tutorial/11
Explore this resource elsewhere: