Basit öğe kaydını göster

dc.contributor.authorDinçer, B.T.
dc.contributor.authorMacdonald, C.
dc.contributor.authorOunis, I.
dc.date.accessioned2020-11-20T16:47:51Z
dc.date.available2020-11-20T16:47:51Z
dc.date.issued2016
dc.identifier.isbn9781450342902
dc.identifier.urihttps://doi.org/10.1145/2911451.2911511
dc.identifier.urihttps://hdl.handle.net/20.500.12809/5942
dc.descriptionSpecial Interest Group on Information Retrieval (ACM SIGIR)en_US
dc.description39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016, 17 July 2016 through 21 July 2016, , 122573en_US
dc.description.abstractA robust retrieval system ensures that user experience is not damaged by the presence of poorly-performing queries. Such robustness can be measured by risk-sensitive evaluation measures, which assess the extent to which a system performs worse than a given baseline system. However, using a particular, single system as the baseline suffers from the fact that retrieval performance highly varies among IR systems across topics. Thus, a single system would in general fail in providing enough information about the real baseline performance for every topic under consideration, and hence it would in general fail in measuring the real risk associated with any given system. Based upon the Chi-squared statistic, we propose a new measure ZRisk that exhibits more promise since it takes into account multiple baselines when measuring risk, and a derivative measure called GeoRisk, which enhances ZRisk by also taking into account the overall magnitude of effectiveness. This paper demonstrates the benefits of ZRisk and GeoRisk upon TREC data, and how to exploit GeoRisk for risk-sensitive learning to rank, thereby making use of multiple baselines within the learning objective function to obtain effective yet risk-averse/robust ranking systems. Experiments using 10,000 topics from the MSLR learning to rank dataset demonstrate the efficacy of the proposed Chi-square statistic-based objective function. © 2016 ACM.en_US
dc.item-language.isoengen_US
dc.publisherAssociation for Computing Machinery, Incen_US
dc.item-rightsinfo:eu-repo/semantics/closedAccessen_US
dc.titleRisk-sensitive evaluation and learning to rank using multiple baselinesen_US
dc.item-typeconferenceObjecten_US
dc.contributor.departmenten_US
dc.contributor.departmentTempDinçer, B.T., Sitki Kocman University of Mugla, Mugla, Turkey; Macdonald, C., University of Glasgow, Glasgow, United Kingdom; Ounis, I., University of Glasgow, Glasgow, United Kingdomen_US
dc.identifier.doi10.1145/2911451.2911511
dc.identifier.startpage483en_US
dc.identifier.endpage492en_US
dc.relation.journalSIGIR 2016 - Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrievalen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US


Bu öğenin dosyaları:

DosyalarBoyutBiçimGöster

Bu öğe ile ilişkili dosya yok.

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster