Temporal Information Retrieval (TIR) at CLEF LongEval 2025

Temporal Information Retrieval (TIR) at CLEF LongEval 2025

Information Retrieval (IR) systems are exposed to constant change. The user queries vary in type and quantity, the media that is searched changes, and even what is today considered relevant might not be anymore tomorrow. Temporal Information Retrieval (TIR) factors these time-dependent features to improve the effectiveness of an IR system. For example, by directly considering the “freshness” of a webpage as a relevance indicator or by extracting the temporal intention of a query to narrow down the result candidates.

CLEF (Conference and Labs of the Evaluation Forum) is an information retrieval conference where specific problem definitions and evaluation datasets are presented for (groups of) people to work on and try to solve the task. In 2024, the CLEF will host the LongEval shared task, which targets the problem of temporal persistence of retrieval systems.

In this thesis project, you could try to develop a retrieval system that takes the temporal dynamics of web search into account. Further, the system could be submitted to the CLEF LongEval shared task.

Abschlussarbeit

Abschluss
B.Sc/M.Sc.
Bearbeiterin
n.a.