In this work we introduce repro_eval - a tool for reactive reproducibility studies of system-oriented information retrieval (IR) experiments. The corresponding Python package provides IR researchers with measures for different levels of reproduction when evaluating their systems' outputs. By offering an easily extensible interface, we hope to stimulate common practices when conducting a reproducibility study of system-oriented IR experiments.
@article{arxiv.2201.07599,
title = {repro_eval: A Python Interface to Reproducibility Measures of System-oriented IR Experiments},
author = {Timo Breuer and Nicola Ferro and Maria Maistro and Philipp Schaer},
journal= {arXiv preprint arXiv:2201.07599},
year = {2022}
}
Comments
Accepted at ECIR21. The final authenticated version is available online at https://doi.org/10.1007/978-3-030-72240-1_51