Published
October 1, 2024
Author(s)
Ian Soboroff, Hui Yang, John Frank
Abstract
Search tasks for professional searchers, such as law enforcement agencies, police officers, and patent examiners, are often more complex than open domain Web search tasks. When professional searchers look for relevant information, it is often the case that they need to go through multiple iterations of searches to interact with a system. The Dynamic Domain Track supports research in dynamic, exploratory search within complex information domains. By providing real- time fine-grained feedback with relevance judgments that was collected during assessing time to the participating systems, we create a dynamic and iterative search process that lasts until the system decides to stop. The search systems are expected to be able to adjust their retrieval algorithms based on the feedback and find quickly relevant information for a multi-faceted information need. This document reports the task, datasets, topic and assessment creation, submissions, and evaluation results for the TREC 2015 Dynamic Domain (DD) Track.
Keywords
information retrieval, dynamic search, domain-specific search
Citation
Soboroff, I. , Yang, H. and Frank, J. (2024), TREC 2015 Dynamic Domain Track Overview, OTHER, National Institute of Standards and Technology, Gaithersburg, MD (Accessed October 2, 2024)
Additional citation formats
Issues
If you have any questions about this publication or are having problems accessing it, please contact [email protected].