How to Measure the Reproducibility of System-oriented IR Experiments

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

  • Fulltext

    Accepted author manuscript, 592 KB, PDF document

  • Timo Breuer
  • Nicola Ferro
  • Norbert Fuhr
  • Maistro, Maria
  • Tetsuya Sakai
  • Philipp Schaer
  • Ian Soboroff

Replicability and reproducibility of experimental results are primary concerns in all the areas of science and IR is not an exception. Besides the problem of moving the field towards more reproducible experimental practices and protocols, we also face a severe methodological issue: we do not have any means to assess when reproduced is reproduced. Moreover, we lack any reproducibility-oriented dataset, which would allow us to develop such methods. To address these issues, we compare several measures to objectively quantify to what extent we have replicated or reproduced a system-oriented IR experiment. These measures operate at different levels of granularity, from the fine-grained comparison of ranked lists, to the more general comparison of the obtained effects and significant differences. Moreover, we also develop a reproducibility-oriented dataset, which allows us to validate our measures and which can also be used to develop future measures.

Original languageEnglish
Title of host publicationSIGIR '20 : Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Number of pages10
PublisherAssociation for Computing Machinery
Publication date2020
Pages349-358
ISBN (Electronic)978-1-4503-8016-4
DOIs
Publication statusPublished - 2020
Event43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 - Virtual, Online, China
Duration: 25 Jul 202030 Jul 2020

Conference

Conference43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020
LandChina
ByVirtual, Online
Periode25/07/202030/07/2020
SponsorACM Special Interest Group on Information Retrieval (SIGIR)

Bibliographical note

Publisher Copyright:
© 2020 ACM.

    Research areas

  • measure, replicability, reproducibility

ID: 269912561