Maura R. GrossmanSelected publications / 2017
Evaluation · Probability sampling · TREC 2016

TREC 2016 Total Recall Track Overview

Maura R. Grossman, Gordon V. Cormack, and Adam Roegiest

The Twenty-Fifth Text REtrieval Conference (TREC 2016), NIST Special Publication 500-321 (2017)

Introduces a statistically sound framework for comparing high-recall review methods in the absence of an infallible gold standard.

Read PDFPublication recordBibTeXPlain citation
Authors
Maura R. Grossman, Gordon V. Cormack, and Adam Roegiest
Published
The Twenty-Fifth Text REtrieval Conference (TREC 2016), NIST Special Publication 500-321 (2017)
Format
Article / scholarly paper

Overview

The TREC Total Recall Track created a common experimental framework for evaluating methods intended to find nearly all relevant documents with reasonable effort. Participating systems selected documents for review, while effectiveness was measured through independent assessment of a probability sample with unequal inclusion probabilities.

This design permitted sound quantitative comparison even though relevance assessments were necessarily incomplete and imperfect. It separated the review method from the evidence used to evaluate it and produced estimates that remained valid in spite of uncertainty in human judgment.

Why this paper matters. A statistically valid comparison does not require an infallible set of relevance assessments. Independent assessment of a properly designed probability sample can provide unbiased estimates of review effectiveness and a fair basis for comparing competing methods in spite of unavoidable uncertainty.

Key contributions

Citation

Maura R. Grossman, Gordon V. Cormack & Adam Roegiest, TREC 2016 Total Recall Track Overview, in The Twenty-Fifth Text REtrieval Conference Proceedings (TREC 2016), NIST Special Publication 500-321 (2017).

Related publications