The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Engineering Quality and Reliability in Technology-Assisted Review
Open accessAbstract
The objective of technology-assisted review ("TAR") is to find as much relevant information as possible with reasonable effort. Quality is a measure of the extent to which a TAR method achieves this objective, while reliability is a measure of how consistently it achieves an acceptable result. We are concerned with how to define, measure, and achieve high quality and high reliability in TAR. When quality is defined using the traditional goal-post method of specifying a minimum acceptable recall threshold, the quality and reliability of a TAR method are both, by definition, equal to the probability of achieving the threshold. Assuming this definition of quality and reliability, we show how to augment any TAR method to achieve guaranteed reliability, for a quantifiable level of additional review effort. We demonstrate this result by augmenting the TAR method supplied as the baseline model implementation for the TREC 2015 Total Recall Track, measuring reliability and effort for 555 topics from eight test collections. While our empirical results corroborate our claim of guaranteed reliability, we observe that the augmentation strategy may entail disproportionate effort, especially when the number of relevant documents is low. To address this limitation, we propose stopping criteria for the model implementation that may be applied with no additional review effort, while achieving empirical reliability that compares favorably to the provably reliable method. We further argue that optimizing reliability according to the traditional goal-post method is inconsistent with certain subjective aspects of quality, and that optimizing a Taguchi quality loss function may be more apt.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“The former estimates the stopping criteria based on the derivation of an estimate of the total number of relevant papers within an initial training set and is considered more reliable than the latter (Cormack & Grossman, 2016; van Haastrecht et al., 2021).”
From Screening Smarter, Not Harder: A Comparative Analysis of Machine Learning Screening Algorithms and Heuristic Stopping Criteria for Systematic Reviews in Educational Research (2024) · cites this paper as Cormack & Grossman, 2016
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Several statistical stopping metrics have been proposed in the literature [15, 21, 22, 35, 38, 49, 50, 53, 55]).”
From The SAFE procedure: a practical stopping heuristic for active learning-based screening in systematic reviews and meta-analyses (2024) · cites this paper as [15]
The cited source says what the claim attributes to it.
In the citing paper
“However, defining a stopping rule is difficult as the cost of labeling additional records must be balanced against the cost of errors made by the model [15].”
From The SAFE procedure: a practical stopping heuristic for active learning-based screening in systematic reviews and meta-analyses (2024) · cites this paper as [15]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
RCV1: A New Benchmark Collection for Text Categorization Research
Lewis, D., Yang, Y., Rose, T. G., & Li, F. (2004) · Goldsmiths (University of London) · doi:10.5555/1005332.1005345 · Cited by 2,503
Finding a "Kneedle" in a Haystack: Detecting Knee Points in System Behavior
Satopaa, V., Albrecht, J., Irwin, D., & Raghavan, B. (2011) · 2011 31st International Conference on Distributed Computing Systems Workshops · doi:10.1109/icdcsw.2011.20 · Cited by 1,274
Introduction to Quality Engineering: Designing Quality into Products and Processes
Taguchi, G. (1986) · Cited by 1,153
An evaluation of retrieval effectiveness for a full-text document-retrieval system
Blair, D. C., & Maron, M. E. (1985) · Communications of the ACM · doi:10.1145/3166.3197 · Cited by 656
Introduction to Quality Engineering: Designing Quality Into Products and Processes
Parr, W. C. (1989) · Technometrics · doi:10.1080/00401706.1989.10488520 · Cited by 629
Lefebvre, C., Manheimer, E., & Glanville, J. (2008) · Cochrane Handbook for Systematic Reviews of Interventions · doi:10.1002/9780470712184.ch6 · Cited by 559
Variations in relevance judgments and the measurement of retrieval effectiveness
Voorhees, E. M. (2000) · Information Processing & Management · doi:10.1016/s0306-4573(00)00010-8 · Cited by 504
The Philosophy of Information Retrieval Evaluation
Voorhees, E. M. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45691-0_34 · Cited by 389
Stemming algorithms: A case study for detailed evaluation
Hull, D. A. (1996) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199601)47:1<70::aid-asi7>3.3.co;2-q · Cited by 369
Efficient construction of large test collections
Cormack, G. V., Palmer, C. R., & Clarke, C. L. A. (1998) · Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/290941.291009 · Cited by 234
Self-citationCan Robots Be Lawyers? Computers, Lawyers, and the Practice of LawPreprint
Remus, D., & Levy, F. S. (2015) · SSRN Electronic Journal · doi:10.2139/ssrn.2701092 · Cited by 157
Evaluation of machine-learning protocols for technology-assisted review in electronic discovery
Cormack, G. V., & Grossman, M. R. (2014) · Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval · doi:10.1145/2600428.2609601 · Cited by 149
Self-citationAutonomy and Reliability of Continuous Active Learning for Technology-Assisted ReviewPreprint
Cormack, G. V., & Grossman, M. R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.06868 · Cited by 98
Self-citationForming test collections with no system pooling
Sanderson, M., & Joho, H. (2004) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1008992.1009001 · Cited by 97
Building a filtering test collection for TREC 2002
Soboroff, I. M., & Robertson, S. E. (2003) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/860435.860481 · Cited by 71
STAIRS redux: Thoughts on the STAIRS evaluation, ten years after
Blair, D. C. (1996) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199601)47:1<4::aid-asi2>3.0.co;2-3 · Cited by 64
Multi-Faceted Recall of Continuous Active Learning for Technology-Assisted Review
Cormack, G. V., & Grossman, M. R. (2015) · Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/2766462.2767771 · Cited by 38
Self-citationOn the choice of effectiveness measures for learning to rank
Yılmaz, E., & Robertson, S. E. (2009) · Information Retrieval · doi:10.1007/s10791-009-9116-x · Cited by 30
Zobel, J., Moffat, A., & Park, L. A. F. (2009) · ACM SIGIR Forum · doi:10.1145/1670598.1670600 · Cited by 28
TREC 2016 Total Recall Track Overview.
Grossman, M. R., Cormack, G. V., & Roegiest, A. (2016) · Text REtrieval Conference · Cited by 28
Self-citationMachine Learning for Information Retrieval: TREC 2009 Web, Relevance Feedback and Legal Tracks.
Cormack, G. V., & Mojdeh, M. (2009) · Cited by 26
Self-citationMachine learning for information retrieval
Si, L., & Jin, R. (2011) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/2009916.2010167 · Cited by 14
Towards minimizing the annotation cost of certified text classification
Bagdouri, M., Webber, W., Lewis, D. D., & Oard, D. W. (2013) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2505515.2505708 · Cited by 14
Research works printed but not linked: 5
- 10.1002/(SICI)1097-4571(199601)47:1%3C4::AID-ASI2%3E3.3.CO;2-5 · doi:10.1002/(sici)1097-4571(199601)47:1<4::aid-asi2>3.3.co;2-5
- M. R. Grossman and G. V. Cormack. Comments on "The implications of Rule 26(g) on the use of technology-assisted review". Fed. Cts. L. Rev., 7:285--312, 2014.
- K. Schieneman and T. Gricks. The implications of Rule 26(g) on the use of technology-assisted review. Fed. Cts. L. Rev., 7:239--274, 2013.
- 10.5555/648264.753539 · doi:10.5555/648264.753539
- E. M. Voorhees and D. K. Harman. The Text REtrieval Conference. In E. M. Voorhees and D. K. Harman, editors, TREC: Experiment and Evaluation in Information Retrieval, pages 3--19. MIT Press, 2005.
Cited by
Bannach-Brown, A., Przybyła, P., Thomas, J., Rice, A. S. C., Ananiadou, S., Liao, J., & Macleod, M. R. (2019) · Systematic Reviews · doi:10.1186/s13643-019-0942-7 · Cited by 185
“Various approaches have been tested [40], but they do not guarantee achieving a desired sensitivity level.”
BackgroundPrioritising references for systematic reviews with RobotAnalyst: A user study
Przybyła, P., Brockmeier, A. J., Kontonatsios, G., Le Pogam, M., McNaught, J., von Elm, E., Nolan, K., & Ananiadou, S. (2018) · Research Synthesis Methods · doi:10.1002/jrsm.1311 · Cited by 148
“Deciding when to stop can be left to the end-user, eg, if the priori-tised references are consistently irrelevant, or heuristics 84 or statistical approaches (based on an unbiased sample of the remaining references) can inform this decision.”
BackgroundBoetje, J., & van de Schoot, R. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02502-7 · Cited by 146
“Several statistical stopping metrics have been proposed in the literature [15, 21, 22, 35, 38, 49, 50, 53, 55]).”
BackgroundSearch strategy formulation for systematic reviews: Issues, challenges and opportunities
MacFarlane, A., Russell‐Rose, T., & Shokraneh, F. (2022) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2022.200091 · Cited by 207
Scalability of Continuous Active Learning for Reliable High-Recall Text Classification
Cormack, G. V., & Grossman, M. R. (2016) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2983323.2983776 · Cited by 100
Self-citation
Metadata
- Authors
- Cormack, G. V., & Grossman, M. R.
- Affiliations
- University of Waterloo (CA)
- Wachtell, Lipton, Rosen & Katz, New York, NY, USA
- Venue
- Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2016-07-07
- Pages
- 75-84
- OpenAlex
- W2341384651
- Cited by
- 98
- References
- 22
- Citations by year
- 2026: 8 · 2025: 6 · 2024: 10 · 2023: 12 · 2022: 8 · 2021: 12 · 2020: 6 · 2019: 13 · 2018: 11 · 2017: 7 · 2016: 5
- FWCI
- 10.19
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion, cc-by-nd)
- Funders
- Natural Sciences and Engineering Research Council (5485 / 2011)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- technology-assisted review, stopping rules, Taguchi loss function, TREC, information retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.