HOBBIT OKE Challenges : Stay tuned and Participate!

Holistic Benchmarking of Big Linked Data

Dear all,

I am happy to inform you that we have two new OKE Challenges for 2017-2018:
* The OKE Open Challenge (https://project-hobbit.us12.list-manage.com/track/click?u=00d040a1bedee64c86d8911b0&id=b7c486fc9b&e=947589bd6f)  2017-2018. We are currently in the training phase of the OKE Open Challenge. The OKE Open Challenge Leaderboard (https://project-hobbit.us12.list-manage.com/track/click?u=00d040a1bedee64c86d8911b0&id=95917ad085&e=947589bd6f) is up and running.  Take the chance to browse the description of the participatingtasks and data sets (https://project-hobbit.us12.list-manage.com/track/click?u=00d040a1bedee64c86d8911b0&id=9e3a7c383a&e=947589bd6f) for the OKE Open Challenge 2017-2018.
* the OKE2018 that will most probably be hosted at ESWC 2018. Please find below a description of the OKE2018 at ESWC.

We will be more than happy if you would like to participate in any of the aforementioned OKE 2017-2018 challenges!

Please contact us for any further information or clarification.

Best regards,

Vassiliki Rentoumi
On behalf of the OKE Challenges team

Description of the OKE2018 at ESWC
We as the former organizers of the OKE Challenge 2017 plan to propose the OKE Challenge 2018 for the upcoming 15th ESWC 2018.

We plan to have the four following tasks:

For each task the knowledge base is DBpedia and a competing system is expected to generate the results in an RDF serialisation.
* Focused Named Entity Identification and Linking This task comprises the identification of named entities in sentences as well as the disambiguation and linking of the identified entities to the knowledge base. The task is limited to three types (Person, Place, Organisation) and their associated subtypes.
* Broader Named Entity Identification and Linking This task extends the first task towards the entity types. Beside the three types in the first task, a competing system might have to identify other types of entities (e.g. Disease, Activity, Language, etc.).
* Relation Extraction This task aims to extract relations between entities from sentences. The given data consists of annotated sentences with entities, i.e., entit mentions, entity types and linkings.
* Knowledge Extraction This task aims to extract knowledge from sentences. The task comprises the identification and linking of named entities as well as the extraction of relations between them.

Copyright © 2017 Hobbit EU project, All rights reserved.

Want to change how you receive these emails?
You can ** update your preferences (https://project-hobbit.us12.list-manage.com/track/click?u=00d040a1bedee64c86d8911b0&id=31eb23aa8d&e=947589bd6f)
or ** unsubscribe from this list (https://project-hobbit.us12.list-manage.com/unsubscribe?u=00d040a1bedee64c86d8911b0&id=1e33221579&e=947589bd6f&c=3132fa7ab0)

Email Marketing Powered by MailChimp

Received on Monday, 18 December 2017 06:14:48 UTC