DIPROMATS 2024 - Shared Task 2: testing data for narrative identification

  1. Peñas, Anselmo 1
  2. Fraile-Hernández, Jesús M. 1
  3. Moral, Pablo 1
  4. Rodrigo, Álvaro 1
  5. Deriu, Jan 2
  6. Sharma, Rajesh 3
  7. Centeno, Roberto 1
  8. Rodríguez-García, Raquel 1
  9. Giedemann, Patrick 2
  10. Reyes-Montesinos, Julio 1
  1. 1 Universidad Nacional de Educación a Distancia
    info
    Universidad Nacional de Educación a Distancia

    Madrid, España

    ROR https://ror.org/02msb5n36

    Geographic location of the organization Universidad Nacional de Educación a Distancia
  2. 2 Zurich University of Applied Sciences
    info
    Zurich University of Applied Sciences

    Winterthur, Suiza

    ROR https://ror.org/05pmsvm27

    Geographic location of the organization Zurich University of Applied Sciences
  3. 3 University of Tartu
    info
    University of Tartu

    Tartu, Estonia

    ROR https://ror.org/03z77qz90

    Geographic location of the organization University of Tartu
+

Editor: Zenodo

Year of publication: 2024

Type: Dataset

Version: 1.0.0

CC BY 4.0

DOI: 10.5281/ZENODO.12663309 lock_openOpen access editor
Dataset versions :
Version Created DOI
1.0.0 05-07-2024 10.5281/zenodo.12663310

Abstract

Narratives are causally connected sequences of events that are selected and evaluated as meaningful for a particular audience. They make sense of the world by identifying the significance of people, places, objects, and events in time. In international relations, international actors create strategic narratives to “construct a shared meaning of the past, present, and future of international politics to shape the behavior of domestic and international actors” DIPROMATS 2024 Task 2 is a multiclass multilabel classification problem. Given a series of predefined narratives of each international actor, systems must determine which narrative the tweets belong to. Systems will receive the description of each narrative and a few examples of tweets in both languages (English and Spanish) that belong to each of them (few-shot learning). A tweet may be associated with one, several or none of the narratives. The few-shot training data can be found here: https://doi.org/10.5281/zenodo.10820961 These are the testing datasets for Englsih and Spanish. They are provided without the keys so the large language models can't be contaminated. If you are interested on testing your system, write anselmo@lsi.uned.es for details on submission and leaderboards.

Funding information

Funders