[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[InetBib] Call for Participation: Shared Task: “Survey Variable Identification in Social Science Publications” (SV-Ident) 2022

Dear colleagues,

You are invited to participate in the Shared Task: “Survey Variable 
Identification in Social Science Publications” (SV-Ident) 2022. This shared 
task is part of the Third Workshop on Scholarly Document Processing (SDP) and 
co-located at COLING 2022.

Shared Task website: https://vadis-project.github.io/sv-ident-sdp2022/

Task Description:

In this shared task, we focus on concepts specific to social science 
literature, namely survey variables. Survey variable mention identification in 
texts can be seen as a multi-label classification problem: Given a sentence in 
a document, and a list of unique variables (from a reference vocabulary of 
survey variables), the task is to classify which variables, if any, are 
mentioned in each sentence. To this end, we divide survey variable 
identification into two sub-tasks:

  *   Task 1 - Variable Detection: identifying whether a sentence contains a 
variable mention or not.
  *   Task 2 - Variable Disambiguation: identifying which variable from a given 
vocabulary is mentioned in a sentence.

The corpus of this task includes multilingual (English and German) trial and 
training datasets, which contain 1,980 and 4,248 instances, respectively. For 
more details, please visit the shared task website.


Please upload a submission file for your classification results to our 
evaluation platform (more details on the shared task website). You can find 
submission information and guidelines on the SDP workshop website.

Important dates:

- Trial data release: March 16, 2022

- Training data release: June 8, 2022

- Deadline for registration: July 4, 2022

- Test data release: July 18, 2022

- System runs due: July 25, 2022

- Workshop papers due: August 15, 2022

- Camera-ready papers due: September 5, 2022

- SDP workshop at COLING 2022: October 16/17, 2022

Useful links:

Shared Task website: https://vadis-project.github.io/sv-ident-sdp2022/

GitHub: https://github.com/vadis-project/sv-ident

Workshop website: https://sdproc.org/2022/sharedtasks.html

Mailing list: <http://www.sdproc.org/> https://groups.google.com/g/svident2022


This task is organized by the VAriable Detection, Interlinking, and 
Summarization (VADIS) project.

Main Organizers:

Tornike Tsereteli, University of Mannheim

Yavuz Selim Kartal, GESIS

Simone Paolo Ponzetto, University of Mannheim

Andrea Zielinski, Fraunhofer ISI

Philipp Mayr, GESIS

Dr. Philipp Mayr
Team Leader Information & Data Retrieval

GESIS - Leibniz Institute for the Social Sciences
Unter Sachsenhausen 6-8,  D-50667 Köln, Germany
Tel: + 49 (0) 221 / 476 94 -533
Email: philipp.mayr@xxxxxxxxx<mailto:philipp.mayr@xxxxxxxxx>
Web: https://www.gesis.org/en/kts

Listeninformationen unter http://www.inetbib.de.