On Correlation to Evaluate QPP - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On Correlation to Evaluate QPP

Résumé

Correlation is widely used to test the hypothesis of the relationship between two variables. In this paper we chose to focus the discussion on query difficulty prediction for which correlation is often used to measure the accuracy of predictors. Here, the correlation is calculated between the actual system effectiveness and the predicted one. Although fairly simple to calculate, the Pearson correlation coefficient can be difficult to interpret and use correctly, especially because of its sensitivity to outliers. This paper illustrates the problem and opens discussion pathways.
Fichier principal
Vignette du fichier
On Correlation to Evaluate QPP.pdf (1.17 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04230663 , version 1 (06-10-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04230663 , version 1

Citer

Josiane Mothe. On Correlation to Evaluate QPP. Query Performance Prediction and Its Evaluation in New Tasks Workshop (QPP++ 2023) co-located with 45th ECIR, Apr 2023, Dublin, Ireland. pp.29-36. ⟨hal-04230663⟩
23 Consultations
12 Téléchargements

Partager

Gmail Facebook X LinkedIn More