Datensatz Zitierlink: 
http://hdl.handle.net/20.500.12708/210281
-
Titel: 
Extended overview of the CLEF 2024 LongEval Lab on Longitudinal Evaluation of Model Performance
en
Zitat: 
Alkhalifa, R., Borkakoty, H., Deveaud, R., El-Ebshihy, A., Espinosa-Anke, L., Fink, T., Galuščáková, P., Gonzalez-Saez, G., Goeuriot, L., Iommi, D., Liakata, M., Tayyar Madabushi, H., Medina-Alias, P., Mulhem, P., Piroi, F., Popel, M., & Zubiaga, A. (2024). Extended overview of the CLEF 2024 LongEval Lab on Longitudinal Evaluation of Model Performance. In Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2024) (pp. 2267–2289). http://hdl.handle.net/20.500.12708/210281
-
Publikationstyp: 
Konferenzbeitrag - Full-Paper Contribution
de
Sprache: 
Englisch
-
Autor_innen: 
Alkhalifa, Rabab 
Borkakoty, Hsuvas 
Deveaud, Romain 
El-Ebshihy, Alaa 
Espinosa-Anke, Luis 
Fink, Tobias 
Galuščáková, Petra 
Gonzalez-Saez, Gabriela 
Goeuriot, Lorraine 
Iommi, David 
Liakata, Maria 
Tayyar Madabushi, Harish 
Medina-Alias, Pablo 
Mulhem, Philippe 
Piroi, Florina 
Popel, Martin 
Zubiaga, Arkaitz 
-
Organisations­einheit: 
E194-04 - Forschungsbereich Data Science 
E058-06 - Fachbereich Zentrum für Forschungsdatenmanagement 
-
Erschienen in: 
Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2024) 
-
Band: 
3740
-
Datum (veröffentlicht): 
5-Aug-2024
-
Veranstaltungs­name: 
Conference and Labs of the Evaluation Forum (CLEF 2024) : Information Access Evaluation meets Multilinguality, Multimodality, and Visualization 
-
Veranstaltungs­zeitraum: 
9-Sep-2024 - 12-Sep-2024
-
Veranstaltungs­ort: 
Grenoble, Frankreich
-
Umfang: 
23
-
Peer Reviewed: 
Ja
-
Keywords: 
Evaluation; Temporal Persistence; Temporal Generalisability; Information Retrieval; Text Classification
en
Abstract: 
We describe the second edition of the LongEval CLEF 2024 shared task. This lab evaluates the temporal persistence of Information Retrieval (IR) systems and Text Classifiers. Task 1 requires IR systems to run on corpora acquired at several timestamps, and evaluates the drop in system quality (NDCG) along these timestamps. Task 2 tackles binary sentiment classification at different points in time, and evaluates the performance drop for different temporal gaps. Overall, 37 teams registered for Task 1 and 25 for Task 2. Ultimately, 14 and 4 teams participated in Task 1 and Task 2, respectively.
en
Forschungs­schwerpunkte: 
Information Systems Engineering: 20%
Computer Science Foundations: 80%
-
Wissenschafts­zweig: 
1020 - Informatik: 90%
5020 - Wirtschaftswissenschaften: 10%
-
Enthalten in den Sammlungen:
Conference Paper

Zur Langanzeige

Seiten Aufrufe

93
aufgerufen am 30.01.2025

Google ScholarTM

Check