How to Robustly Combine Judgements from Crowd Assessors with AWARE
Publikation: Bidrag til tidsskrift › Konferenceartikel › fagfællebedømt
We propose the Assessor-driven Weighted Averages for Retrieval Evaluation (AWARE) probabilistic framework, a novel methodology for dealing with multiple crowd assessors, who may be contradictory and/or noisy. By modeling relevance judgements and crowd assessors as sources of uncertainty, AWARE directly combines the performance measures computed on the ground-truth generated by the crowd assessors instead of adopting some classification technique to merge the labels produced by them. We propose several unsupervised estimators that instantiate the AWARE framework and we compare them with Majority Vote (MV) and Expectation Maximization (EM) showing that AWARE approaches improve both in correctly ranking systems and predicting their actual performance scores.
Originalsprog | Engelsk |
---|---|
Tidsskrift | CEUR Workshop Proceedings |
Vol/bind | 2161 |
Sider (fra-til) | 1DUMMY |
ISSN | 1613-0073 |
Status | Udgivet - 1 jan. 2018 |
Eksternt udgivet | Ja |
Begivenhed | 26th Italian Symposium on Advanced Database Systems, SEBD 2018 - Castellaneta Marina (Taranto), Italien Varighed: 24 jun. 2018 → 27 jun. 2018 |
Konference
Konference | 26th Italian Symposium on Advanced Database Systems, SEBD 2018 |
---|---|
Land | Italien |
By | Castellaneta Marina (Taranto) |
Periode | 24/06/2018 → 27/06/2018 |
Sponsor | CC ICT-SUD |
ID: 216516836