Crowd-Machine Collaboration for Item Screening

Dades bibliogràfiques
Parent link:World Wide Web Conference (WWW 2018).— 2018.— [P. 95-96]
Autor corporatiu: Национальный исследовательский Томский политехнический университет Школа инженерного предпринимательства
Altres autors: Krivosheev E. Evgeny, Harandizadeh B. Bahareh, Benatallah B. Boualem, Casati F. Fabio
Sumari:Title screen
In this paper we describe how crowd and machine classifier can beefficiently combined to screen items that satisfy a set of predicates.We show that this is a recurring problem in many domains, presentmachine-human (hybrid) algorithms that screen items efficientlyand estimate the gain over human-only or machine-only screeningin terms of performance and cost.
Idioma:anglès
Publicat: 2018
Matèries:
Accés en línia:https://doi.org/10.1145/3184558.3186946
Format: Electrònic Capítol de llibre
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=659537