Effective user interaction for high-recall retrieval: Less is more
High-recall retrieval---finding all or nearly all relevant documents---is critical to applications
such as electronic discovery, systematic review, and the construction of test collections for …
such as electronic discovery, systematic review, and the construction of test collections for …
TARexp: A python framework for technology-assisted review experiments
Technology-assisted review (TAR) is an important industrial application of information
retrieval (IR) and machine learning (ML). While a small TAR research community exists, the …
retrieval (IR) and machine learning (ML). While a small TAR research community exists, the …
When to stop reviewing in technology-assisted reviews: Sampling from an adaptive distribution to estimate residual relevant documents
D Li, E Kanoulas - ACM Transactions on Information Systems (TOIS), 2020 - dl.acm.org
Technology-Assisted Reviews (TAR) aim to expedite document reviewing (eg, medical
articles or legal documents) by iteratively incorporating machine learning algorithms and …
articles or legal documents) by iteratively incorporating machine learning algorithms and …
Evaluating sentence-level relevance feedback for high-recall information retrieval
This study uses a novel simulation framework to evaluate whether the time and effort
necessary to achieve high recall using active learning is reduced by presenting the reviewer …
necessary to achieve high recall using active learning is reduced by presenting the reviewer …
A heuristic sampling method for maintaining the probability distribution
Sampling is a fundamental method for generating data subsets. As many data analysis
methods are developed based on probability distributions, maintaining distributions when …
methods are developed based on probability distributions, maintaining distributions when …
Stopping criteria for technology assisted reviews based on counting processes
A Sneyd, M Stevenson - Proceedings of the 44th international ACM …, 2021 - dl.acm.org
Technology Assisted Review (TAR) aims to minimise the manual judgements required to
identify relevant documents. Reductions in workload are dependent on a reviewer being …
identify relevant documents. Reductions in workload are dependent on a reviewer being …
[PDF][PDF] UWaterlooMDS at the TREC 2017 Common Core Track.
In this report, we discuss the experiments we conducted for the TREC 2017 Common Core
Track. We implemented a High-Recall retrieval system for assessors to e ciently nd relevant …
Track. We implemented a High-Recall retrieval system for assessors to e ciently nd relevant …
Comparison of Tools and Methods for Technology-Assisted Review
T O'Halloran, B McManus, A Harbison… - International Conference …, 2024 - Springer
In a large-scale eDiscovery effort in Irish litigation, human assessors participated in two
technology-assisted reviews (“TAR”) employing continuous active learning (“CAL”) …
technology-assisted reviews (“TAR”) employing continuous active learning (“CAL”) …
Computer-Assisted Cohort Identification in Practice
The standard approach to expert-in-the-loop machine learning is active learning, where,
repeatedly, an expert is asked to annotate one or more records and the machine finds a …
repeatedly, an expert is asked to annotate one or more records and the machine finds a …
Increasing the Efficiency of High-Recall Information Retrieval
H Zhang - 2019 - uwspace.uwaterloo.ca
The goal of high-recall information retrieval (HRIR) is to find all, or nearly all, relevant
documents while maintaining reasonable assessment effort. Achieving high recall is a key …
documents while maintaining reasonable assessment effort. Achieving high recall is a key …