Skip to Main content Skip to Navigation
Conference papers

IRIT at CheckThat! 2018

Abstract : The 2018 CLEF CheckThat! is composed of two tasks: (1) Check-Worthiness and (2) Factuality. We participated to task (1) only which purpose is to evaluate the check-worthiness of claims in political debates. Our method to achieve this goal is to represent each claim by a vector of five computed values that correspond to scores on five criteria. These vectors are then used with machine learning algorithms to classify claims as check-worthy or not. We submitted three runs using different machine learning algorithms. The best result we achieved using the offi-cial measure MAP ranks our primary run the 12th over the 16 submitted runs. Our first contrastive run is ranked 2nd with the Mean Precision@1 measure.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02289947
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Tuesday, September 17, 2019 - 11:39:17 AM
Last modification on : Tuesday, September 8, 2020 - 10:42:05 AM
Long-term archiving on: : Sunday, February 9, 2020 - 12:16:41 AM

File

agez_22448.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02289947, version 1
  • OATAO : 22448

Citation

Romain Agez, Clément Bosc, Cédric Lespagnol, Josiane Mothe, Noémie Petitcol. IRIT at CheckThat! 2018. 9th Conference and Labs of the Evaluation Forum, Living Labs (CLEF 2018), Sep 2018, Avignon, France. ⟨hal-02289947⟩

Share

Metrics

Record views

22

Files downloads

14