[CFP] ISWC Semantic Web Challenge - SMART2022

SMART2022 - Subtasks for Question Answering over Knowledge Graphs
    ISWC 2022 Semantic Web Challenge [https://iswc2022.semanticweb.org/]

*Brief Background*
Knowledge Base Question Answering (KBQA) is a popular task in the field of
Natural Language Processing and Information Retrieval, in which the goal is
to answer a natural language question using the facts in a Knowledge Base.
KBQA can involve several subtasks such as entity linking, relation linking,
and answer type prediction. In the SMART 2022 Semantic Web Challenge, we
focus on evaluating modules for three subtasks in KBQA: Entity Linking,
Relation Linking and Answer Type Prediction.

***************************************************
Website: https://smart-task.github.io/2022/
Datasets: https://github.com/smart-task/smart-2022-datasets/
Slack: https://smart-task-iswc.slack.com/
Conference date and location: 23 - 27 October 2022 (Virtual)
Submission deadline: *September 16, 2022*
****************************************************

*Task Descriptions*
This year, in the third iteration of the SMART challenge, we have three
independent tasks:

Task 1 - Answer Type Prediction: Given a question in natural language, the
task is to predict the type of the answer using a set of candidates from a
target ontology.

* Which languages were influenced by Perl? -> dbo:ProgrammingLanguage or
wd:Q9143
* How many employees does IBM have? -> number

Task 2 - Relation Linking: Given a question in natural language, the task is
to predict the relations needed to extract the correct answer from the KB.

* Who are the actors starring in movies directed by and starring William
Shatner? -> dbo:starring, dbo:director  or cast member (P161), director
(P57)
* What games can be played in schools founded by Fr. Orlando? -> dbo:sport,
dbo:foundedBy or founded by (P112), sport (P641)

Task 3 - Entity Linking: Given a question in natural language, the task is
to identify the entities and link them to the KG, so that those entities
can be used for formulating the query.
- Was Ganymede discovered by Galileo Galilei? -> [dbr:Ganymede_(moon),
dbr:Galileo_Galilei]
- Where was richard sprigg steuart born? -> [wd:Q7329193(Richard Sprigg
Steuart)]

*Datasets*
We have created four datasets for each task, each KB; SMART-2022-AT
(DBpedia and Wikidata) and SMART-2022-RL (DBpedia and Wikidata),
SMART2022-EL (DBpedia and Wikidata). Participants can compete in all or any
combination of these six datasets.

*Submissions and publication*
The participants are supposed to send their system outputs by the deadline.
Participants can submit a system paper that will be peer-reviewed and
published in a CEUR volume similar to the last two years -
http://ceur-ws.org/Vol-2774/ and http://ceur-ws.org/Vol-3119/.

Please join the slack workspace and contact the organizers regarding any
inquiries related to the task, datasets, and submissions.

We are looking forward to your submissions!

*Organizers*
Nandana Mihindukulasooriya, IBM Research AI
Mohnish Dubey, Philips Research
Alfio Gliozzo, IBM Research AI
Jens Lehmann, Amazon
Axel-Cyrille Ngonga Ngomo, Paderborn University
Ricardo Usbeck, University of Hamburg
Gaetano Rossiello, IBM Research AI
Debayan Banerjee, University of Hamburg