Call for Challenge Participation

1st Challenge on Linked Data for Information Extraction
organized in connection with the LD4IE workshop
at ISWC 2014, Riva del Garda, Italy

http://data.dws.informatik.uni-mannheim.de/LD4IE/

Submissions due September 12, 2014

*The best solution is awarded a Springer book voucher worth 250€!*
----------------------------------------------------------------------

The Linked Data for Information Extraction challenge explores how structured data on web pages can be used to train information extraction systems extracting that information from other sources as well. It is based on a subset of the Web Data Commons Microformats dataset [1].

For the challenge, original annotated pages are provided, as well as the triples extracted from them. Based on that information, participants have to design an information extraction system for extracting that information from other web pages. In this year's challenge, we focus on hCard data [2], i.e., information about persons. The use case of such a system could be the assembly of a large database on person data.

The systems are evaluated on a test set of annotated web pages, from which all annotations have been removed. The participants have to extract triples from those pages and send in their resulting triple files. The submitted files are evaluated against the gold standard of the original triples, ranking the solutions by F-measure.

A short description of each solution is included in the LD4IE workshop proceedings, and presented at the workshop [3].

For more detail on the datasets, tasks, results/paper submission and evaluation, see
http://data.dws.informatik.uni-mannheim.de/LD4IE/

[1] http://webdatacommons.org/structureddata/index.html
[2] http://microformats.org/wiki/hcard
[3] http://oak.dcs.shef.ac.uk/ld4ie2014/

----------------------------------------------------------------------
Organization:

Heiko Paulheim, University of Mannheim, Germany
Robert Meusel, University of Mannheim, Germany