This paper presents a possible approach for the LongEval Lab of the CLEF 2023 conference concerning Longitudinal Evaluation of Model Performance. Studies have shown that the performance of Information Retrieval systems decreases as the time gap between the test data and the training data increases. The LongEval Lab focuses on the development of a robust temporal IR system that improves such performance.
SEUPD@CLEF: Team NEON. A Memoryless Approach To Longitudinal Evaluation
Ferro N.
2023
Abstract
This paper presents a possible approach for the LongEval Lab of the CLEF 2023 conference concerning Longitudinal Evaluation of Model Performance. Studies have shown that the performance of Information Retrieval systems decreases as the time gap between the test data and the training data increases. The LongEval Lab focuses on the development of a robust temporal IR system that improves such performance.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
paper-189.pdf
accesso aperto
Tipologia:
Published (publisher's version)
Licenza:
Creative commons
Dimensione
1.2 MB
Formato
Adobe PDF
|
1.2 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
