Corpus Subsampling: Estimating the Effectiveness of Neural Retrieval Models on Large Corpora.

@inproceedings{frobe-2025-corpus, author = {Maik Fr\"{o}be and Andrew Parry and Harrisen Scells and Shuai Wang and Shengyao Zhuang and Guido Zuccon and Martin Potthast and Matthias Hagen}, editor = {Claudia Hauff and Craig Macdonald and Dietmar Jannach and Gabriella Kazai and Franco Maria Nardini and Fabio Pinelli and Fabrizio Silvestri and Nicola Tonellotto}, title = {{Corpus Subsampling: Estimating the Effectiveness of Neural Retrieval Models on Large Corpora}}, booktitle = {{Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6-10, 2025, Proceedings, Part I}}, series = {Lecture Notes in Computer Science}, volume = {15572}, pages = {453--471}, publisher = {Springer}, year = {2025}, url = {https://doi.org/10.1007/978-3-031-88708-6_29}, doi = {https://doi.org/10.1007/978-3-031-88708-6_29} }