Reliability Measurement without Limits
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
In computational linguistics, a reliability measurement of 0.8 on some statistic such as κ is widely thought to guarantee that hand-coded data is fit for purpose, with 0.67 to 0.8 tolerable, and lower values suspect. We demonstrate that the main use of such data, machine learning, can tolerate data with low reliability as long as any disagreement among human coders looks like random noise. When the disagreement introduces patterns, however, the machine learner can pick these up just like it picks up the real patterns in the data, making the performance figures look better than they really are. For the range of reliability measures that the field currently accepts, disagreement can appreciably inflate performance figures, and even a measure of 0.8 does not guarantee that what looks like good performance really is. Although this is a commonsense result, it has implications for how we work. At the very least, computational linguists should look for any patterns in the disagreement among coders and assess what impact they will have.
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.
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
Assessing Agreement on Classification Tasks: The Kappa Statistic
Carletta, J. (1996) · arXiv · doi:10.48550/arxiv.cmp-lg/9602004 · Cited by 2,088 · cited 1×
“He uses a specific reliability statistic, α , for his measurements, but Carletta (1996) implicitly assumes kappa-like metrics are similar enough in practice for the rule of thumb to apply to them as well.”
Self-citationInter-Coder Agreement for Computational Linguistics
Artstein, R., & Poesio, M. (2008) · Computational Linguistics · doi:10.1162/coli.07-034-r2 · Cited by 1,665
Reliability in content analysis: some common misconceptions and recommendations.
Krippendorff, K. (2004) · Human Communication Research · doi:10.1093/hcr/30.3.411 · Cited by 1,027 · cited 2×
“As Krippendorff (2004, page 429) recommends, one should test reliability for the “distinctions that matter” and perform “suitable experiments of the effects of unreliable data on the conclusions.””
InfluentialThe Kappa Statistic: A Second Look
Eugenio, B. D., & Glass, M. (2004) · Computational Linguistics · doi:10.1162/089120104773633402 · Cited by 489
Cited by
Inter-Coder Agreement for Computational Linguistics
Artstein, R., & Poesio, M. (2008) · Computational Linguistics · doi:10.1162/coli.07-034-r2 · Cited by 1,665
The “Problem” of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation
Plank, B. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.731 · Cited by 121
Multiplicity and word sense: evaluating and learning from multiply labeled word sense annotations
Passonneau, R. J., Bhardwaj, V., Salleb-Aouissi, A., & Ide, N. (2012) · Language Resources and Evaluation · doi:10.1007/s10579-012-9188-x · Cited by 34
The ALICO corpus: analysing the active listener
Malisz, Z., Włodarczak, M., Buschmeier, H., Skubisz, J., Kopp, S., & Wagner, P. (2016) · Language Resources and Evaluation · doi:10.1007/s10579-016-9355-6 · Cited by 23
“This degree of agreement is commonly regarded as ‘fair’ to ‘moderate’ (Landis and Koch 1977), and is usually considered to be insufficient for annotation of linguistic data (cf. Reidsma and Carletta 2008).”
BackgroundPatton, D., Blandfort, P., Frey, W., Gaskell, M., & Karaman, S. (2019) · Proceedings of the Annual Hawaii International Conference on System Sciences · doi:10.24251/hicss.2019.260 · Cited by 23
Metadata
- Authors
- Reidsma, D., & Carletta, J.
- Venue
- Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2008-09
- Volume
- 34
- Issue
- 3
- Pages
- 319-326
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W2091950237
- Cited by
- 106
- References
- 4
- FWCI
- 7.49
- Type
- journal article
- Language
- en
- Open access
- bronze
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Reliability Measurement without Limits. https://app.cochat.ai/papers/10.1162/coli.2008.34.3.319
- The paper
- Reidsma, D., & Carletta, J. (2008). Reliability Measurement without Limits. Computational Linguistics. https://doi.org/10.1162/coli.2008.34.3.319
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.