SemEval-2018 Performance Results with Statistical Validation

Performance metrics from the SemEval-2018 evaluation campaign. The dataset includes 95% confidence intervals calculated via 10-fold cross-validation to reflect result variability. It was authored by Weiguang Dong and last updated on April 27, 2026.

Use Cases

• Benchmarking NLP system performance based on SemEval-2018 results
• Analyzing result variability based on reported confidence intervals
• Comparing model robustness based on cross-validation metrics

Strengths

• Includes statistical validation via 95% confidence intervals
• Employs 10-fold cross-validation methodology
• Released under a permissive CC-BY-4.0 license

Limitations

• Dataset is very small at 5.5 KB, indicating limited scope
• Row count and column-level documentation are absent
• Description metadata is limited; actual data quality requires manual inspection after download

Provenance

Source

figshare

Collection Method

Likely contains aggregated performance results from the SemEval-2018 shared tasks.

Time Range

Covers the SemEval-2018 evaluation period.

Freshness

Last updated 2026-04-27 17:22:26

Geography

null