UMBC ebiquity

Graph of Relations

Status: Past project

Project Description:

 

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.

Online demonstration

Start Date: January 2010

End Date: January 2014

Principal Investigator:
Tim Finin

Faculty:
Anupam Joshi

Students:
Lushan Han

Tags: semantic web, rdf, natural language, natural language processing

 

There are 10 associated publications:  Hide the list...

8 Refereed Publications

2014

1. 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, 116 downloads.

2. Lushan Han, "Schema Free Querying of Semantic Data", PhdThesis, University of Maryland, Baltimore County, August 2014, 39 downloads.

2013

3. 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, 850 downloads.

4. 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, 1156 downloads.

2012

5. 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, 434 downloads.

2011

6. Lushan Han et al., "GoRelations: An Intuitive Query System for DBpedia", InProceedings, Proceedings of the Joint International Semantic Technology Conference, December 2011, 680 downloads.

2009

7. Lushan Han et al., "Finding Semantic Web Ontology Terms from Words", InProceedings, Proceedings of the Eigth International Semantic Web Conference, October 2009, 1259 downloads.

2008

8. Lushan Han et al., "Predicting Appropriate Semantic Web Terms from Words", InProceedings, Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, July 2008, 1048 downloads.

2 Non-Refereed Publications

2012

1. Lushan Han et al., "GoRelations: Towards an Intuitive Query System for RDF Data", TechReport, University of Maryland, Baltimore County, February 2012, 432 downloads.

2011

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.

 

Research Areas:
 Language technology
 Machine learning
 Semantic Web
 Web based information systems

 

Assertions:

  1. (Project) Graph of Relations has a dataset (Resource) UMBC webbase corpus