Graph of Relations
Status: Past project
Users need better ways to explore linked open data collections and obtain information from it. Using SPARQL requires not only mastering its syntax and semantics but also understanding the RDF data model, the ontology used by the DBpedia, and URIs for entities of interest. Natural language question answering systems solve the problem, but these are still subjects of research. We are developing a compromise approach in which non-experts specify a graphical ``skeleton'' for a query and annotate it with freely chosen words, phrases and entity names. The combination reduces ambiguity and allows us to reliably produce an interpretation that can be translated into SPARQL. We have demonstrated the approach's feasibility for DBpedia with an implementation that performs well in an evaluation using queries from the 2011 QALD workshop. Key contributions are the robust methods that combine statistical association and semantic similarity to map user terms to the most appropriate classes and properties used in the DBpedia ontology.
Start Date: January 2010
End Date: January 2014
There are 14 associated publications: Hide the list...
12 Refereed Publications
1. Abhay L. Kashyap et al., "Robust Semantic Text Similarity Using LSA, Machine Learning and Linguistic Resources", Article, Language Resources and Evaluation, March 2016, 443 downloads.
2. Zareen Syed et al., "Querying Large Linked Data Resources", InProceedings, 14th International Semantic Web Conference, October 2015, 279 downloads.
3. Lushan Han et al., "Querying RDF Data with Text Annotated Graphs", InProceedings, Proceedings of the 27th International Conference on Scientific and Statistical Database Management, June 2015, 544 downloads.
4. Zareen Syed et al., "UMBC_Ebiquity-SFQ: Schema Free Querying System ", InProceedings, Proceedings of the Semantic Web Evaluation Challenge, ESWC, June 2015, 289 downloads.
5. Abhay L. Kashyap et al., "Meerkat Mafia: Multilingual and Cross-Level Semantic Textual Similarity systems", InProceedings, Proceedings of the 8th International Workshop on Semantic Evaluation, August 2014, 1060 downloads.
6. Lushan Han, "Schema Free Querying of Semantic Data", PhdThesis, University of Maryland, Baltimore County, August 2014, 456 downloads.
7. Lushan Han et al., "UMBC_EBIQUITY-CORE: Semantic Textual Similarity Systems", InProceedings, Proceedings of the Second Joint Conference on Lexical and Computational Semantics, June 2013, 2196 downloads.
8. Lushan Han et al., "Improving Word Similarity by Augmenting PMI with Estimates of Word Polysemy", Article, IEEE Transactions on Knowledge and Data Engineering (TKDE), June 2013, 1596 downloads.
9. Lushan Han et al., "Schema-Free Structured Querying of DBpedia Data", InProceedings, Proceedings of the 21st ACM Conference on Information and Knowledge Management (CIKM), August 2012, 762 downloads.
10. Lushan Han et al., "GoRelations: An Intuitive Query System for DBpedia", InProceedings, Proceedings of the Joint International Semantic Technology Conference, December 2011, 1116 downloads.
11. Lushan Han et al., "Finding Semantic Web Ontology Terms from Words", InProceedings, Proceedings of the Eigth International Semantic Web Conference, October 2009, 1532 downloads.
12. Lushan Han et al., "Predicting Appropriate Semantic Web Terms from Words", InProceedings, Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, July 2008, 1384 downloads.
2 Non-Refereed Publications
1. Lushan Han et al., "GoRelations: Towards an Intuitive Query System for RDF Data", TechReport, University of Maryland, Baltimore County, February 2012, 695 downloads.
2. Lushan Han et al., "Improving Word Similarity by Augmenting PMI with Estimates of Word Polysemy", TechReport, University of Maryland, Baltimore County, June 2011.
There are 5 associated resources: Hide the list...
1. GoRelations: an Intuitive Query System for DBPedia (and LOD), Presentation.
2. Making the Semantic Web Easier to Use , Presentation.
3. Making the Semantic Web Easier to Use for Sharing Science Data, Presentation.
4. UMBC webbase corpus, Dataset.
5. Word and phrase similarity, Demonstration.