Please use this identifier to cite or link to this item:
Title: Efficient Test Collection Construction via Active Learning
Authors: Rahman, M. M.
Kutlu, Mücahid
Elsayed, T.
Lease, M.
Keywords: Active learning
information retrieval
test collections
Issue Date: Sep-2020
Publisher: Association for Computing Machinery
Source: Rahman, M. M., Kutlu, M., Elsayed, T., and Lease, M. (2020, September). Efficient test collection construction via active learning. In Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval (pp. 177-184).
Abstract: To create a new IR test collection at low cost, it is valuable to carefully select which documents merit human relevance judgments. Shared task campaigns such as NIST TREC pool document rankings from many participating systems (and often interactive runs as well) in order to identify the most likely relevant documents for human judging. However, if one's primary goal is merely to build a test collection, it would be useful to be able to do so without needing to run an entire shared task. Toward this end, we investigate multiple active learning strategies which, without reliance on system rankings: 1) select which documents human assessors should judge; and 2) automatically classify the relevance of additional unjudged documents. To assess our approach, we report experiments on five TREC collections with varying scarcity of relevant documents. We report labeling accuracy achieved, as well as rank correlation when evaluating participant systems based upon these labels vs. full pool judgments. Results show the effectiveness of our approach, and we further analyze how varying relevance scarcity across collections impacts our findings. To support reproducibility and follow-on work, we have shared our code online\footnote\url © 2020 ACM.
ISBN: 978-145038067-6
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Show full item record

CORE Recommender

Page view(s)

checked on Feb 6, 2023

Google ScholarTM



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