Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/4029
Title: ArTest: The First Test Collection for Arabic Web Search with Relevance Rationales
Authors: Hasanain, M.
Barkallah, Y.
Suwaileh, R.
Kutlu, Mücahid
Elsayed, T.
Keywords: ad-hoc search
evaluation
less-resourced language
retrieval
Publisher: Association for Computing Machinery, Inc
Source: Hasanain, M., Barkallah, Y., Suwaileh, R., Kutlu, M., and Elsayed, T. (2020, July). Artest: The first test collection for arabic web search with relevance rationales. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 2017-2020).
Abstract: The scarcity of Arabic test collections has long hindered information retrieval (IR) research over the Arabic Web. In this work, we present ArTest, the first large-scale test collection designed for the evaluation of ad-hoc search over the Arabic Web. ArTest uses ArabicWeb16, a collection of around 150M Arabic Web pages as the document collection, and includes 50 topics, 10,529 relevance judgments, and (more importantly) a rationale behind each judgment. To our knowledge, this is also the first IR test collection that includes rationales of primary assessors (i.e., topic developers) for their relevance judgments, exhibiting a useful resource for understanding the relevance phenomena. Finally, ArTest is made publicly-available for the research community. © 2020 ACM.
URI: https://hdl.handle.net/20.500.11851/4029
https://dl.acm.org/doi/10.1145/3397271.3401223
ISBN: 978-145038016-4
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record



CORE Recommender

SCOPUSTM   
Citations

2
checked on Mar 23, 2024

WEB OF SCIENCETM
Citations

2
checked on Jan 20, 2024

Page view(s)

126
checked on Mar 25, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.