Downloaded 25 times
![Ontology , RDF• Ontology provides a means to vocabulariesand link’s semantics on linked data.• RDF provides a generic, graph-based datamodel to structure and link data thatdescribes things• A triple [subject, predicate, object]– Subject: a URI– Predicate: a URI– Object: a URI or a string literal12](/image.pl?url=https%3a%2f%2fimage.slidesharecdn.com%2fquestionansweringinlinkeddata-130923005814-phpapp01%2f75%2fQuestion-answering-in-linked-data-12-2048.jpg&f=jpg&w=240)
Uploaded byReza Ramezani
PPTX, PDF661 views
Question answering in linked data
The document discusses the evolution of the web from documents to data, and introduces linked data which publishes machine-readable data on the web that is explicitly defined and linked to other datasets. It then discusses question answering systems that take natural language questions and locate answers from document collections, including both closed-domain systems with restricted knowledge bases and open-domain systems that retrieve answers from the web. The document also presents the linked data technology stack and some examples of linked open data clouds from 2007 to 2011 to demonstrate the growth of linked data on the web.
Recommended
More Related Content
What's hot
Viewers also liked
Similar to Question answering in linked data
More from Reza Ramezani
Question answering in linked data
- 2.
- 3.The Web ofDocuments Traditional Web, Hypertext Web Analogy A global file system Designed for Human consumption Primary objects Documents Links Untyped Between documents (or parts of documents) Degree of structure in object Fairy low Semantics of content and links implicit3
- 4.The Web ofDocuments4
- 5.The Web ofData Analogy A global data space Designed for Machines first, humans later Primary objects Things (description of things) Links Typed Between things Degree of structure in objects High Semantic of content and links Explicit5
- 6.The Web ofLinked Data6
- 7.Linked Data• Isabout using the Web to create typed linksbetween data from different sources• Refers to data published on the Web insuch a way that– It is machine-readable– Its meaning is explicitly defined– It is linked to other datasets– It can be linked to from external datasets7
- 8.Properties of theWeb of Data• It is generic– Can contain any type of data• Data about anything– Anyone can publish data– No constraints on choice of vocabularies– entities are connected by RDF links8
- 9.A Taste ofLinked Data9
- 10.A Taste ofLinked Data (Cont.)10
- 11.Linked Data TechnologyStackURIHTTPRDFS / OWLRDF / RDF Links11
- 12.Ontology , RDF•Ontology provides a means to vocabulariesand link’s semantics on linked data.• RDF provides a generic, graph-based datamodel to structure and link data thatdescribes things• A triple [subject, predicate, object]– Subject: a URI– Predicate: a URI– Object: a URI or a string literal12
- 13.LOD Cloud :May 200713
- 14.LOD Cloud :July 200714
- 15.LOD Cloud :August 200715
- 16.LOD Cloud :November 200716
- 17.LOD Cloud :February 200817
- 18.LOD Cloud :March 200918
- 19.LOD Cloud :July 200919
- 20.LOD Cloud :September 201020
- 21.LOD Cloud :September 201121
- 22.Retrieval Process22• a)Query construction• b) Search algorithm of the system• c) Presentation of the resultsSearch EnginesQuery A lot of related Web PagesQA SystemsQuestion Exact Answer
- 23.Retrieval Process (Cont.)23QueryAnalyzerQueryA lot ofWeb PagesWWWCrawlerRequestWeb PagesIndexFileIndexerWeb PagesIndex TermsSearchRankingResults DocDatastoreWeb PagesUIQueryRanked ResultsWeb Pages• Traditional SE
- 24.Some Problems24• Informationsearch with search engines
- 25.Therefore, what isneeded?25• Assign meta data to information objects• Content description with concepts and relations betweenthem• Provision of background knowledge• Provision of the semantics of relations for queryextension, ontology integration, etc.RDFRDF Schema, OWL, Rules
- 26.26Question Answering• Questionanswering (QA) systems take users’natural language questions and automatically locateanswers from large collections of documents.• Two types of QA systems– Closed-Domain (or restricted domain) Question Answering– Open-Domain Question Answering
- 27.27Question Answering (Cont.)•Open Domain QA SystemQuestionAnalysisAnswerSelectionQuestion QueryAnswerTypeDocumentsAnswer (s)QuestionAnswer (s)UIDocumentAnalysisPassagesDocument RetrievalSystemsDocumentRetrievalOpen DomainOntology
- 28.28Question Answering (Cont.)•Restricted Domain QA SystemQuestionAnalysisAnswerPost ProcessingQuestion QueryAnswer (s)QuestionAnswer (s)UIAnswerRetrievalAnswer (s)DataOpen DomainOntologyLexiconDomainOntologyKnowledge Base
- 29.Related Works• AquaLog–Vanessa Lopez, Victoria Uren, Enrico Motta, Michele Pasin.• PowerAqua– Vanessa Lopez, Andriy Nikolov, Marta Sabou, Victoria Uren, Enrico Motta,Mathieu d’Aquin• QASYO– for YAGO Ontology• AutoSPARQL29
- 30.
- 31.