This is the report based on the work done for LongEval Task 1: Retrieval at CLEF 2023, by team Squid (whose participants are from the University of Padua). Information retrieval (IR) systems have played an increasingly important role in our society and people’s daily lives. Although they have become more and more powerful during the last decades, their temporal persistence is still causing drops in performance, thus failing to achieve good temporal generalisability. To investigate and improve the resolution of this issue, in this paper, we present and discuss the various solutions submitted to the first CLEF 2023 shared task (LongEval-Retrieval), which precisely requires the development of temporal information retrieval systems.
SEUPD@CLEF: Team Squid on LongEval-Retrieval
Ferro N.
2023
Abstract
This is the report based on the work done for LongEval Task 1: Retrieval at CLEF 2023, by team Squid (whose participants are from the University of Padua). Information retrieval (IR) systems have played an increasingly important role in our society and people’s daily lives. Although they have become more and more powerful during the last decades, their temporal persistence is still causing drops in performance, thus failing to achieve good temporal generalisability. To investigate and improve the resolution of this issue, in this paper, we present and discuss the various solutions submitted to the first CLEF 2023 shared task (LongEval-Retrieval), which precisely requires the development of temporal information retrieval systems.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
