Overview - Dynamic Domain 2015

Proceedings | Data | Runs | Participants

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.

Track coordinator(s):

• Hui Yang, Georgetown University
• John Frank, Diffeo and MIT
• Ian Soboroff, National Institute of Standards and Technology (NIST)

Track Web Page: http://trec-dd.org

---