Browse wiki

Jump to: navigation, search
Logic-based question answering
Abstract Question answering systems aim to provide Question answering systems aim to provide concise and correct responses to arbitrary questions, communicating with the user in a natural language. This way they help making the knowledge of large textual sources accessible in an intuitive manner which goes beyond the capabilities of conventional search engines. In the LogAnswer project the universities of Hagen and Koblenz cooperate to build a German language question answering system which combines computational linguistics and automated reasoning to deduce answers from a knowledge base derived from Wikipedia.m a knowledge base derived from Wikipedia.
Added by wikilit team Added on initial load  +
Collected data time dimension Cross-sectional  +
Conclusion LogAnswer achieved an accuracy (percentageLogAnswer achieved an accuracy (percentage of answers deemed correct) of 14.5% [14]. Even though the prototype was not yet competitive with the senior participants (the top accuracy rating among German language systems was 37%), the participation has revealed necessary changes to the system, and it has given us the comprehensive set of questions and answers for continued internal evaluation of LogAnswer.ontinued internal evaluation of LogAnswer.
Data source Experiment responses  + , Wikipedia pages  +
Doi 10.1007/s13218-010-0010-x +
Google scholar url http://scholar.google.com/scholar?ie=UTF-8&q=%22Logic-based%2Bquestion%2Banswering%22  +
Has author Ulrich Furbach + , Ingo Glöckner + , Hermann Helbig + , Björn Pelzer +
Has domain Computer science +
Has topic Computational linguistics +
Issue 1  +
Month April  +
Pages 51-55  +
Peer reviewed Yes  +
Publication type Journal article  +
Published in KI – Künstliche Intelligenz +
Research design Design science  +
Research questions In the LogAnswer project the universities of Hagen and Koblenz cooperate to build a German language question answering system which combines computational linguistics and automated reasoning to deduce answers from a knowledge base derived from Wikipedia.
Revid 10,861  +
Theories Undetermined
Theory type Design and action  +
Title Logic-based question answering
Unit of analysis Article  +
Url http://dx.doi.org/10.1007/s13218-010-0010-x  +
Volume 24  +
Wikipedia coverage Sample data  +
Wikipedia data extraction Dump  +
Wikipedia language German  +
Wikipedia page type Article  +
Year 2010  +
Creation dateThis property is a special property in this wiki. 15 March 2012 20:29:33  +
Categories Computational linguistics  + , Computer science  + , Publications with missing comments  + , Publications  +
Modification dateThis property is a special property in this wiki. 30 January 2014 20:29:33  +
hide properties that link here 
  No properties link to this page.
 

 

Enter the name of the page to start browsing from.