Overview of the 2019 open-source IR replicability challenge (OSIRRC 2019)

Overview of the 2019 open-source IR replicability challenge (OSIRRC 2019)

Clancy, Ryan (University of Waterloo)
Ferro, Nicola (Università degli Studi di Padova)
Hauff, C. (TU Delft Web Information Systems)
Lin, Jimmy (University of Waterloo)
Sakai, Tetsuya (Waseda University)
Wu, Ze Zhong (University of Waterloo)

Clancy, Ryan (editor)
Ferro, Nicola (editor)
Hauff, Claudia (editor)
Lin, Jimmy (editor)
Sakai, Tetsuya (editor)
Wu, Ze Zhong (editor)

2019

The Open-Source IR Replicability Challenge (OSIRRC 2019), organized as a workshop at SIGIR 2019, aims to improve the replicability of ad hoc retrieval experiments in information retrieval by gathering a community of researchers to jointly develop a common Docker specification and build Docker images that encapsulate a diversity of systems and retrieval models. We articulate the goals of this workshop and describe the "jig" that encodes the Docker specification. In total, 13 teams from around the world submitted 17 images, most of which were designed to produce retrieval runs for the TREC 2004 Robust Track test collection. This exercise demonstrates the feasibility of orchestrating large, community-based replication experiments with Docker technology. We envision OSIRRC becoming an ongoing community-wide effort to ensure experimental replicability and sustained progress on standard test collections.

http://resolver.tudelft.nl/uuid:e2d15ec5-7d04-4b03-964e-4de873c9284d

CEUR-WS.org

OSIRRC 2019 The Open-Source IR Replicability Challenge: Proceedings of the Open-Source IR Replicability Challenge (OSIRRC 2019) co-located with 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019)

2019 Open-Source IR Replicability Challenge, OSIRRC 2019, 2019-07-25, Paris, France

CEUR Workshop Proceedings, 1613-0073, 2409

Institutional Repository

conference paper

© 2019 Ryan Clancy, Nicola Ferro, C. Hauff, Jimmy Lin, Tetsuya Sakai, Ze Zhong Wu