Semantic Web Challenge @ ISWC 2010 - Call for Participation

Dear all,

we are happy to announce the Semantic Web Challenge 2010!

The Semantic Web Challenge 2010 is collocated with the 9th International
Semantic Web Conference (ISWC2010) in Shanghai, China. As last year, the
challenge consists of two tacks: The Open Track and the Billion Triples
Track, which requires participants to make use of the data set that has been
crawled from the public Semantic Web. The data set consists of 3.2 billion
triples this year and can be downloaded from the challenge's website.   

The Call for Participation is found below. More information about the
Challenge is provided at

http://challenge.semanticweb.org/

We are looking forward to your submissions which as we hope will make the
Semantic Web Challenge again one of the most exciting events at ISWC.

Best regards,

Diana and Chris


----------------------------------------------------------

Call for Participation for the 

8th Semantic Web Challenge 

at the 9th International Semantic Web Conference ISWC 2010 
Shanghai, China, November 7-11, 2010 

http://challenge.semanticweb.org/

----------------------------------------------------------

Introduction

Submissions are now invited for the 8th annual Semantic Web Challenge, the
premier event for demonstrating practical progress towards achieving the
vision of the Semantic Web. The central idea of the Semantic Web is to
extend the current human-readable Web by encoding some of the semantics of
resources in a machine-processable form. Moving beyond syntax opens the door
to more advanced applications and functionality on the Web. Computers will
be better able to search, process, integrate and present the content of
these resources in a meaningful, intelligent manner. 

As the core technological building blocks are now in place, the next
challenge is to demonstrate the benefits of semantic technologies by
developing integrated, easy to use applications that can provide new levels
of Web functionality for end users on the Web or within enterprise settings.
Applications submitted should give evidence of clear practical value that
goes above and beyond what is possible with conventional web technologies
alone. 

As in previous years, the Semantic Web Challenge 2010 will consist of two
tracks: the Open Track and the Billion Triples Track. The key difference
between the two tracks is that the Billion Triples Track requires the
participants to make use of the data set (consisting of 3.2 billion triples
this year) that has been crawled from the Web and is provided by the
organizers. The Open Track has no such restrictions. As before, the
Challenge is open to everyone from industry and academia. The authors of the
best applications will be awarded prizes and featured prominently at special
sessions during the conference. 

The overall goal of this event is to advance our understanding of how
Semantic Web technologies can be exploited to produce useful applications
for the Web. Semantic Web applications should integrate, combine, and deduce
information from various sources to assist users in performing specific
tasks. 

-------------------
Challenge Criteria

The Challenge is defined in terms of minimum requirements and additional
desirable features that submissions should exhibit. The minimum requirements
and the additional desirable features are listed below per track. 

Open Track

Minimal requirements

1. The application has to be an end-user application, i.e. an application
that provides a practical value to general Web users or, if this is not the
case, at least to domain experts. 
2. The information sources used 
should be under diverse ownership or control 
should be heterogeneous (syntactically, structurally, and semantically), and

should contain substantial quantities of real world data (i.e. not toy
examples). 
The meaning of data has to play a central role. 
3. Meaning must be represented using Semantic Web technologies. 
4. Data must be manipulated/processed in interesting ways to derive useful
information and this semantic information processing has to play a central
role in achieving things that alternative technologies cannot do as well, or
at all; 

Additional Desirable Features 

In addition to the above minimum requirements, we note other desirable
features that will be used as criteria to evaluate submissions. 

1. The application provides an attractive and functional Web interface (for
human users) 
2. The application should be scalable (in terms of the amount of data used
and in terms of distributed components working together). Ideally, the
application should use all data that is currently published on the Semantic
Web. 
3. Rigorous evaluations have taken place that demonstrate the benefits of
semantic technologies, or validate the results obtained. 
4. Novelty, in applying semantic technology to a domain or task that have
not been considered before 
5. Functionality is different from or goes beyond pure information retrieval

6. The application has clear commercial potential and/or large existing user
base 
7. Contextual information is used for ratings or rankings 
8. Multimedia documents are used in some way 
9. There is a use of dynamic data (e.g. workflows), perhaps in combination
with static information 
10. The results should be as accurate as possible (e.g. use a ranking of
results according to context) 
11. There is support for multiple languages and accessibility on a range of
devices 

Billion Triples Track 

The specific goal of the Billion Triples Track is to demonstrate the
scalability of applications as well as the capability to deal with the
specifics of data that has been crawled from the public Web. We stress that
the goal of this is not to be a benchmarking effort between triple stores,
but rather to demonstrate applications that can work on Web scale using
realistic Web-quality data. 

Minimal requirements 

The primary goal of the Billion Triple track is to demonstrate applications
that can work on Web scale using realistic Web-quality data. 

1. The applications must make use of the Billion Triple Challenge 2010
dataset provided by the organisers, which has been crawled from the Web and
consists of 3.2 billion triples this year. The functionality of the
applications is left open: for example it could involve helping people
figure out what is in the dataset via browsing, visualization, profiling,
etc., or inferencing that adds information not directly queryable in the
original dataset. 
2. The tool or application is allowed to use other data that can be linked
to the Billion Triple Challenge 2010 dataset, but there is still an
expectation that the primary focus will be on the data provided. 
3. The tool or application does not have to be specifically an end-user
application, as defined for the Open Track Challenge, but usability is a
concern. The key goal is to demonstrate an interaction with the large
data-set driven by a user or an application. 

Additional Desirable Features

In addition to the above minimum requirements, we note other desirable
features that will be used as criteria to evaluate submissions. 

1. The application should do more than simply store/retrieve large numbers
of triples 
2. The application or tool(s) should be scalable (in terms of the amount of
data used and in terms of distributed components working together) 
3. The application or tool(s) should show the use of the very large, mixed
quality data set 
4. The application should either function in real-time or, if
pre-computation is needed, have a real-time realization (but we will take a
wide view of "real time" depending on the scale of what is done) 

------------------
How to participate

Visit http://challenge.semanticweb.org in order to participate and register
for the Semantic Web Challenge by submitting the required information as
well as a link to the application on the online registration form. The form
will open in August 2010 and will be open until Friday 1 October, 2010. 

The following information must be provided: 
1. Abstract: no more than 200 words. 
2. Description: The description should show details of the system, including
why the system is innovative, which features or functions the system
provides, what design choices were made and what lessons were learned. The
description must include an appendix of 1-2 pages summarising explicitly how
participants have addressed the evaluation requirements (including mandatory
and any relevant desirable criteria). Papers should not exceed eight pages
and must be formatted according to the same guidelines as the papers in the
Research Track (see http://iswc2010.semanticweb.org/). 
3. Web access: The application should be accessible via the web. If the
application is not publicly accessible, passwords should be provided. A
(short) set of instructions on how to start and use the application should
also be provided on the web page. 

Descriptions (including the appendix) will be published in the form of
online proceedings on the Semantic Web Challenge website. 

------
Prizes

All participants are required to present their systems at a specific poster
session at the ISWC 2010 conference. A jury consisting of experts from
industry and academia will judge the systems at the conference. A monetary
prize will be provided to the winners of each track, along with publicity
for their work. The winners will also be asked to give a live demonstration
of their application at the closing ceremony of the ISWC 2010 conference.
The best applications will have a chance to appear as full articles in the
Journal of Web Semantics. 

In the event that one of the tracks receive less than a minimal number of
submissions, the organizers reserve the right to merge the two tracks of the
competition. 

---------------
Important Dates 

* Friday 1 October 2010 Submissions due 
* November 7-11: ISWC 2010 Technical Program 


For questions and further information about the challenge please contact:

Christian Bizer (chris@bizer.de) 
Diana Maynard (diana@dcs.shef.ac.uk) 

Received on Monday, 31 May 2010 08:41:56 UTC