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 …

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 …

Technology-Assisted Reviews (TAR) aim to expedite document reviewing (eg, medical
articles or legal documents) by iteratively incorporating machine learning algorithms and …

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 …

Sampling is a fundamental method for generating data subsets. As many data analysis
methods are developed based on probability distributions, maintaining distributions when …

Technology Assisted Review (TAR) aims to minimise the manual judgements required to
identify relevant documents. Reductions in workload are dependent on a reviewer being …

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 …

In a large-scale eDiscovery effort in Irish litigation, human assessors participated in two
technology-assisted reviews (“TAR”) employing continuous active learning (“CAL”) …

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 …

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 …