Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models

D. Cohen, B. Mitra, Oleg Lesota, Navid Rekabsaz, Carsten Eickhoff

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Original language	English
Title of host publication	Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery
Pages	654 - 664
Number of pages	11
ISBN (Print)	9781450380379
DOIs	https://doi.org/10.1145/3404835.3462951
Publication status	Published - Jul 2021

Fields of science

Cohen, D., Mitra, B., Lesota, O., Rekabsaz, N., & Eickhoff, C. (2021). Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021) (pp. 654 - 664). Article 3462951 Association for Computing Machinery. https://doi.org/10.1145/3404835.3462951

@inproceedings{f2f05fa940614b2883905f88f1e3c8fa,

title = "Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models",

author = "D. Cohen and B. Mitra and Oleg Lesota and Navid Rekabsaz and Carsten Eickhoff",

year = "2021",

month = jul,

doi = "10.1145/3404835.3462951",

language = "English",

isbn = "9781450380379",

pages = "654 -- 664",

booktitle = "Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)",

publisher = "Association for Computing Machinery",

}

Cohen, D, Mitra, B, Lesota, O, Rekabsaz, N & Eickhoff, C 2021, Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models. in Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)., 3462951, Association for Computing Machinery, New York, NY, USA, pp. 654 - 664. https://doi.org/10.1145/3404835.3462951

Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models. / Cohen, D.; Mitra, B.; Lesota, Oleg et al.
Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). New York, NY, USA: Association for Computing Machinery, 2021. p. 654 - 664 3462951.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

TY - GEN

T1 - Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models

AU - Cohen, D.

AU - Mitra, B.

AU - Lesota, Oleg

AU - Rekabsaz, Navid

AU - Eickhoff, Carsten

PY - 2021/7

Y1 - 2021/7

U2 - 10.1145/3404835.3462951

DO - 10.1145/3404835.3462951

M3 - Conference proceedings

SN - 9781450380379

SP - 654

EP - 664

BT - Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)

PB - Association for Computing Machinery

CY - New York, NY, USA

ER -

Cohen D, Mitra B, Lesota O, Rekabsaz N, Eickhoff C. Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021). New York, NY, USA: Association for Computing Machinery. 2021. p. 654 - 664. 3462951 doi: 10.1145/3404835.3462951