Can we predict QPP? An approach based on multivariate outliers - Gestion des Données Access content directly
Conference Papers Year : 2024

Can we predict QPP? An approach based on multivariate outliers

Abstract

Query performance prediction (QPP) aims to forecast the effectiveness of a search engine across a range of queries and documents. While state-of-the-art predictors offer a certain level of precision, their accuracy is not flawless. Prior research has recognized the challenges inherent in QPP but often lacks a thorough qualitative analysis. In this paper, we delve into QPP by examining the factors that influence the predictability of query performance accuracy. We propose the working hypothesis that while some queries are readily predictable, others present significant challenges. By focusing on outliers, we aim to identify the queries that are particularly challenging to predict. To this end, we employ multivariate outlier detection method. Our results demonstrate the effectiveness of this approach in identifying queries on which QPP do not perform well, yielding less reliable predictions. Moreover, we provide evidence that excluding these hard-to-predict queries from the analysis significantly enhances the overall accuracy of QPP.
Fichier principal
Vignette du fichier
ECIR_2024_Short_Outliers___QPP.pdf (860.99 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04465059 , version 1 (19-02-2024)

Identifiers

  • HAL Id : hal-04465059 , version 1

Cite

Adrian-Gabriel Chifu, Sébastien Dejean, Moncef Garouani, Josiane Mothe, Diego Ortiz, et al.. Can we predict QPP? An approach based on multivariate outliers. 46th European Conference on Information Retrieval (ECIR 2024), Graham McDonald; Craig Macdonald; Iadh Ounis, Mar 2024, Glasgow, United Kingdom. à paraître. ⟨hal-04465059⟩
37 View
8 Download

Share

Gmail Facebook X LinkedIn More