Task definition: Given a check-worthy claim in the form of a tweet, and a set of previously fact-checked claims, rank the previously fact-checked claims in order of usefulness to fact-check the input claim. You can find all the details for the dataset, format checker, scorer and baselines from this CLEF2022-CheckThat! Task 2, for the git repo.
The current version are listed bellow corresponds to the release of the training, dev and test sets.
You can find all the dataset,
This task is evaluated as a ranking task. Ranked list per claim will be evaluated using ranking evaluation measures (MAP@k for k=1,3,5,10,20,all, MRR and Precision@k for k=1,3,5,10,20). Official measure is MAP@5.
The baselines module contains a random and a simple BM25 IR baseline for the task.
| Model | subtask-2A--English | subtask-2A--Arabic | subtask-2B--English |
|---|---|---|---|
| Random Baseline | 0.0000 | 0.0000 | |
| Ngram Baseline | 0.8179 | 0.3207 |
This page enumerated the terms and conditions of the competition.
Start: April 22, 2022, midnight
Description: Subtask-2A-English--Evaluation
Start: April 22, 2022, midnight
Description: Subtask-2B-English--Evaluation
Start: April 22, 2022, midnight
Description: Subtask-2A-Arabic--Evaluation
May 6, 2022, 11:59 p.m.
You must be logged in to participate in competitions.
Sign In