Quantcast

[CfP] WSDM Cup 2017: Knowledge Base Quality and Search

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
1 message Options
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[CfP] WSDM Cup 2017: Knowledge Base Quality and Search

Martin Potthast

-------------------------------------------------------------------------------
WSDM Cup 2017: Call for Participation
-------------------------------------------------------------------------------

We invite you to take part in one of the following shared tasks:


Task 1.
Vandalism Detection -- Given a Wikidata revision, is it damaging?
This task is about detecting vandalism as well as all other kinds of damaging
edits to Wikidata. In doing so, not only Wikidata's integrity is protected, but
also that of all information systems making use of the knowledge base..


Task 2.
Triple Scoring -- Compute relevance scores for triples from type-like relations.
For example, the triple "Johnny_Depp profession Actor" should get a high score,
because acting is Depp's main profession, whereas "Quentin_Tarantino profession
Actor" should get a low score, because Tarantino is more of a director than an
actor. Such scores are a basic ingredient for ranking results in entity search. 




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

now open         Registration
Sep    1, 2016   Training data release
Dec    8, 2016   Final software submission
Dec   22, 2016   Announcement of evaluation results
Jan    5, 2017   Paper submission
Feb 6-10, 2017   Conference and WSDM Cup workshop

All deadlines are 11:59 PM, anywhere on earth (AoE).


-------------------------------------------------------------------------------
Special Announcements
-------------------------------------------------------------------------------

Evaluation as a Service.

For the sake of reproducability, we ask you to submit your software instead of
just its run output. Software submissions allow for preserving your software
in working condition, and for re-evaluating it as new datasets appear.
To facilitate software submissions, we will make use of the cloud-based
evaluation platform TIRA (www.tira.io)..

Open Source Proceedings.

We encourage the open source release of your software. To maximize the impact
of your software, we collect it at a central repository on GitHub:
Private repositories can be assigned to you at request during the competition.

Benefits for early birds.

Submitting your software or your notebook early, as well as registering early
for the conference will be rewarded. Check out the specific benefits on
Loading...