Call for Systems: Question Answering over Linked Data (QALD-7)

QALD2017 CHALLENGE @ ESWC 2017

ESWC 2017, May 28th, 2016 to June 1st, 2017 Portoroz, Slovenia.
https://project-hobbit.eu/challenges/qald2017/

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

The main task of QALD therefore is the following: Given one or several 
RDF dataset(s) as
well as additional knowledge sources and natural language questions or 
keywords,
return the correct answers or a SPARQL query that retrieves these answers.

In order to focus on specific aspects and challenges, we propose the 
following three tasks:

Task 1: Multilingual question answering over DBpedia
Task 2: Hybrid question answering
Task 3: Large-Scale question answering over RDF
Task 4: Wikidata-based question answering

More details on the different tasks can be found here: 
https://project-hobbit.eu/challenges/qald2017/

Submission

The QALD challenge provides an automatic evaluation tool (GERBIL QA 
integrated into the HOBBIT platform)
that is open source and available for everyone to re-use. This tool is 
accessible online, so that
participants can simply upload the answers produced by their system or 
even check their system via a web
service.

Each experiment will have a citable, time-stable and archivable URI 
which is both human- and machine-
readable. It is mandatory for each system to provide an endpoint URL 
wrapped inside a provided Docker
container after the submission in order to be evaluated with GERBIL QA.

We are accepting papers (up to 5 pages) describing the submitted 
approach and evaluation results.
Submissions must be in English and in PDF, formatted in the style of the 
Springer Publications format for
Lecture Notes in Computer Science (LNCS).

Papers should be submitted through the EasyChair system (TBA) no later 
than midnight Friday March 10th,
2017, Hawaii Time. Submissions will be reviewed by members of the 
challenge program committee. Papers will
be evaluated according to their significance, originality, technical 
content, style, clarity, and relevance
to the challenge. The complete set of papers will be published with the 
CEUR Workshop Proceedings (CEUR-
WS.org), listed by the DBLP.

For any questions, please write an email to Ricardo Usbeck (usbeck AT 
informatik.uni-leipzig.de).

Preliminary Schedule

Release of training data and instructions:    Friday January 13th, 2017
Release of test dataset:    Friday April 7th, 2017
Paper submission deadline:    Friday March 10th, 2017
Challenge paper reviews:    Tuesday April 5th, 2017
Paper Notifications and invitation to task:    Friday April 7th, 2017
Camera ready papers (5 pages document):    Sunday April 23rd, 2017
Submission of camera-ready papers:    April 24, 2014

Received on Thursday, 19 January 2017 15:56:56 UTC