Tables to Linked Data

Status: Active project

Project Description:
Vast amounts of information is encoded in tables found in documents, on the Web, and in spreadsheets or databases. Integrating or searching over this information benefits from understanding its intended meaning and making it explicit in a semantic representation language like RDF. Most current approaches to generating Semantic Web representations from tables requires human input to create schemas and often results in graphs that do not follow best practices for linked data. Evidence for a table’s meaning can be found in its column headers, cell values, implicit relations between columns, caption and surrounding text but also requires general and domain-specific background knowledge. We describe techniques grounded in graphical models and probabilistic reasoning to infer meaning associated with a table. Using background knowledge from the Linked Open Data cloud, we jointly infer the semantics of column headers, table cell values (e.g., strings and numbers) and relations between columns and represent the inferred meaning as graph of RDF triples. A table’s meaning is thus captured by mapping columns to classes in an appropriate ontology, linking cell values to literal constants, implied measurements, or entities in the linked data cloud (existing or new) and discovering or and identifying relations between columns.

Start Date: September 2010

End Date: May 2013

Faculty:
Anupam Joshi

Students:
Varish Mulwad

Tags: semantic web, learning, entity recognition, linked data

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

9 Refereed Publications

2011

1. Varish Mulwad et al., "Automatically Generating Government Linked Data from Tables", InCollection, Working notes of AAAI Fall Symposium on Open Government Knowledge: AI Opportunities and Challenges, November 2011, 272 downloads.

2. Varish Mulwad, "DC Proposal: Graphical Models and Probabilistic Reasoning for Generating Linked Data from Tables", InProceedings, Proceedings of Tenth International Semantic Web Conference, Part II, October 2011, 222 downloads.

3. Varish Mulwad et al., "Generating Linked Data by Inferring the Semantics of Tables", InProceedings, Proceedings of the First International Workshop on Searching and Integrating New Web Data Sources, September 2011, 414 downloads.

2010

4. Varish Mulwad et al., "Using linked data to interpret tables", InProceedings, Proceedings of the the First International Workshop on Consuming Linked Data, November 2010, 592 downloads.

5. Varish Mulwad et al., "T2LD: Interpreting and Representing Tables as Linked Data ", InProceedings, Proceedings of the Poster and Demonstration Session at the 9th International Semantic Web Conference, CEUR Workshop Proceedings, November 2010, 717 downloads.

6. Varish Mulwad, "T2LD - An automatic framework for extracting, interpreting and representing tables as Linked Data", MastersThesis, UMBC, August 2010, 594 downloads.

7. Zareen Syed et al., "Exploiting a Web of Semantic Data for Interpreting Tables", InProceedings, Proceedings of the Second Web Science Conference, April 2010, 1466 downloads.

2008

8. Lushan Han et al., "RDF123: from Spreadsheets to RDF", InProceedings, Seventh International Semantic Web Conference, October 2008, 2277 downloads.

2007

9. Cynthia Parr et al., "RDF123 and Spotter: Tools for generating OWL and RDF for biodiversity data in spreadsheets and unstructured text", InProceedings, Proceedings of Biodiversity Information Standards Annual Conference (TDWG 2007), October 2007, 956 downloads.

1 Non-Refereed Publication

2007

1. Lushan Han et al., "RDF123: a mechanism to transform spreadsheets to RDF", TechReport, University of Maryland, Baltimore County, August 2007, 4327 downloads.

There are 13 associated resources:  Hide the list...

1. Automatically Generating Linked Data from Tables, Presentation.

2. Generating Linked Data by inferring the semantics of tables , Poster.

3. Generating Linked Data by inferring the semantics of tables, Poster.

4. Generating Linked Data by inferring the semantics of tables, Presentation.

5. Making the Semantic Web Easier to Use , Presentation.

6. Making the Semantic Web Easier to Use for Sharing Science Data, Presentation.

7. RDF123 Google Group, Google group.

8. RDF123 java application v1.0, Executable.

9. RDF123 linux application v1.0, Executable.

10. RDF123 presentation, Presentation.

11. RDF123 windows application v1.0, Executable.

12. Tables to Linked Data, Presentation.

13. Tables to Linked Data, Presentation.

Research Areas:
 Machine learning
 Semantic Web
 Web based information systems