W3C home > Mailing lists > Public > public-lod@w3.org > May 2020

CfP: ISWC 2020 Challenge - SeMantic AnsweR Type prediction (SMART) task.

From: usbeck <ricardo.usbeck@uni-paderborn.de>
Date: Tue, 26 May 2020 13:40:17 +0200
Message-Id: <C880A879-7455-4EDE-B1B9-AFF1BCAA764C@uni-paderborn.de>
** Apologies for cross-posting **

ISWC 2020 Challenge - SeMantic AnsweR Type prediction (SMART) task
- in conjunction with ISWC 2020 https://iswc2020.semanticweb.org/ <https://iswc2020.semanticweb.org/> 

*********************************************************************************

Challenge website: https://smart-task.github.io/ <https://smart-task.github.io/> 
Conference date and location: 2-6 November 2020, (Online - Virtual)
Submission deadline: August 17, 2020

*********************************************************************************

# Background

SMART task is focused on answer type prediction. Question or answer type classification plays a key role in question answering. The questions can be generally classified based on Wh-terms (Who, What, When, Where, Which, Whom, Whose, Why). Similarly, the answer type classification is determining the type of the expected answer based on the query. Such answer type classifications in literature have been performed as a short-text classification task using a set of coarse-grained types, for instance, either 6 or 50 types within the TREC QA task. A granular answer type classification is possible with popular Semantic Web ontologies such as DBpedia (~760 classes) and Wikidata (~50K classes).

# Task Description
In this challenge, 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. e.g.,

Who is the heaviest player of the Chicago Bulls? -> dbo:BasketballPlayer
How many employees does IBM have? -> number
When did Margaret Mead marry Gregory Bateson? -> date

# Datasets
We have created two datasets; one using the DBpedia ontology and the other using the Wikidata ontology each containing 21,964 questions and 22,822 questions respectively. Systems can participate using only one dataset or both. 

# Organizers
Mohnish Dubey, University of Bonn
Alfio Gliozzo, IBM Research AI
Jens Lehmann, University of Bonn
Nandana Mihindukulasooriya, IBM Research AI
Axel-Cyrille Ngonga Ngomo, Universit├Ąt Paderborn
Ricardo Usbeck, Fraunhofer IAIS Dresden


Received on Tuesday, 26 May 2020 11:40:37 UTC

This archive was generated by hypermail 2.4.0 : Tuesday, 26 May 2020 11:40:38 UTC