We introduce the second edition of the CheckThat! Lab, part of the 2019 Cross-Language Evaluation Forum (CLEF). CheckThat! proposes two complementary tasks. Task 1: predict which claims in a political debate should be prioritized for fact-checking. Task 2: rank Web-retrieved pages against a check-worthy claim based on their usefulness for fact-checking, extract useful passages from those pages, and then use them all to decide whether the claim is factually true or false. Checkthat! provides a full evaluation framework, consisting of data in English (derived from fact-checking sources) and Arabic (gathered and annotated from scratch) and evaluation based on mean average precision (MAP) for ranking and F 1 for classification tasks.
CheckThat! at CLEF 2019: Automatic identification and verification of claims / Elsayed T.; Nakov P.; Barron-Cedeno A.; Hasanain M.; Suwaileh R.; Da San Martino G.; Atanasova P.. - ELETTRONICO. - 11438:(2019), pp. 309-315. (Intervento presentato al convegno 41st European Conference on Information Retrieval, ECIR 2019 tenutosi a deu nel 2019) [10.1007/978-3-030-15719-7_41].
CheckThat! at CLEF 2019: Automatic identification and verification of claims
Barron-Cedeno A.;Da San Martino G.;
2019
Abstract
We introduce the second edition of the CheckThat! Lab, part of the 2019 Cross-Language Evaluation Forum (CLEF). CheckThat! proposes two complementary tasks. Task 1: predict which claims in a political debate should be prioritized for fact-checking. Task 2: rank Web-retrieved pages against a check-worthy claim based on their usefulness for fact-checking, extract useful passages from those pages, and then use them all to decide whether the claim is factually true or false. Checkthat! provides a full evaluation framework, consisting of data in English (derived from fact-checking sources) and Arabic (gathered and annotated from scratch) and evaluation based on mean average precision (MAP) for ranking and F 1 for classification tasks.File | Dimensione | Formato | |
---|---|---|---|
Barron-Cedeno.pdf
Open Access dal 08/04/2020
Tipo:
Postprint
Licenza:
Licenza per accesso libero gratuito
Dimensione
555.78 kB
Formato
Adobe PDF
|
555.78 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.