Scalable Question Answering Open Challenge (SQA) 2017-2018

Challenge Motivation & Overview

After the successful organization of the QALD-7 challenge at the ESWC 2017 and the QALD-8 challenge incorporated in the NLIWoD workshop at ISWC 2017, with more than 50 participants, the HOBBIT project is proud to announce the Scalable Question Answering Open Challenge (SQA) over Linked Data. SQA Open Challenge will run periodically with cutoff dates in June  2018 (coinciding with ESWC 2018) and November 2018. Therewith, the challenge will ensure continuous participation and system evaluation.

  1. Monetary prizes will be provided to the best winning systems at each cutoff date.
  2. Stay tuned to get ready to participate!      Express your interest!

Prizes

The winner of the challenge will receive a prize of 250€.

Q&A

Contact Email: Giulio.Napolitano@iais.fraunhofer.de

 Important Dates

Dry-Run phase: December 2017 to January 2018
Release of the test questions
without answers:
TBA
Training Phase*: February to  April 2018
Test Phase: May 2018
Proclamation of results: June 3rd, 2018

*Weekly release of evaluation results from the end of January onwards.

Tasks and Training Data

The key challenge for Scalable Question Answering over Linked Data is in the need to translate a user’s information request into such a form that it can be efficiently evaluated using standard Semantic Web query processing and inferencing techniques.

Therefore, the main task of SQA Open Challenge is the following: given an RDF dataset and and a large volume of natural language questions or keywords, return the correct answers (or SPARQL queries that retrieves those answers).

Small test Data and Documentation are available for SQA :

In the Scalable Question Answering Open Challenge (SQA) users can display the capabilities of their systems using the HOBBIT platform provided by the homonymous H2020 project.

Registration and Submission

TBA

Organization

  • Giulio Napolitano, IAIS Fraunhofer, Germany
  • Axel-Cyrille Ngonga Ngomo, University of Paderborn, Germany
  • Ricardo Usbeck, University of Paderborn, Germany

—————————————————————————————————
Scalable Question Answering Open Challenge (SQA) 2017 – 2018
—————————————————————————————————

After the successful organization of the QALD-7 challenge at the ESWC 2017 and the QALD-8 challenge incorporated in the NLIWoD workshop at ISWC 2017, with more than 50 participants, the HOBBIT project (https://project-hobbit.eu/) is proud to announce the Scalable Question Answering Open Challenge (SQA) over Linked Data. SQA Open Challenge will run periodically with cutoff dates in June  2018 (coinciding with ESWC 2018) and November 2018. Therewith, the challenge will ensure continuous participation and system evaluation. Stay tuned and get ready to participate!

  1. Monetary prizes will be provided to the best winning systems at each cutoff date.
  2. Please express your interest in SQA Open Challenge by adding your email via the link: https://project-hobbit.eu/open-challenges/sqa-open-challenge/express-interestYou will receive further information and notifications regarding the progress of SQA Open Challenge.

—————————————————————————————————-
Important Dates
—————————————————————————————————

Dry run phase:                                  December 2017 to January 2018
Release of the test questions
without answers:                               TBA
Training phase*:                                February to April 2018
Test phase:                                          May 2018
Proclamation of results:                   June 3rd, 2018

*Weekly release of evaluation results from the end of January onwards.

—————————————————————————————————
Prizes
—————————————————————————————————
The winner of the challenge will get a prize of 250€

—————————————————————————————————
Scalable Question Answering Open Challenge at a glance
—————————————————————————————————
The key challenge for Scalable Question Answering over Linked Data is in the need to translate a user’s information request into such a form that it can be efficiently evaluated using standard Semantic Web query processing and inferencing techniques.

Therefore, the main task of SQA Open Challenge is the following: given an RDF dataset and and a large volume of natural language questions or keywords, return the correct answers (or SPARQL queries that retrieves those answers).

Small test Data and Documentation are available for SQA Open Challenge:
* Sample dataset: http://hobbitdata.informatik.uni-leipzig.de/SQAOC/sqaoc-sample-largescale.json
* Description: http://hobbitdata.informatik.uni-leipzig.de/SQAOC/Documentation.txt

In the Scalable Question Answering Open Challenge (SQA) users can display the capabilities of their systems using the HOBBIT platform (https://project-hobbit.eu/outcomes/hobbit-platform) provided by the homonymous H2020 project.

——————————————————————————–
Organization
——————————————————————————–

* Giulio Napolitano, IAIS, Fraunhofer, Germany
* Axel-Cyrille Ngonga Ngomo, University of Paderborn, Germany
* Ricardo Usbeck, University of Paderborn, Germany

——————————————————————————–
Further Information and Contact
——————————————————————————–

For detailed information including datasets and submission guidelines,
please visit the challenge website:  https://project-hobbit.eu/open-challenges/sqa-open-challenge/
Contact Email: Giulio.Napolitano@iais.fraunhofer.de