Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Factual Consistency EvaluationSE
Kendall's Tau37.4
22
Keyphrase ExtractionSE-2010 (test)
F1 Score48.65
12
Word Sense DisambiguationSE13 (test)
F1 Score81.2
8
Word Sense DisambiguationSE07 (dev)
F1 Score74.9
8
Information ExtractionSE 10-PDF subsample
F1 Score45.25
6
Information ExtractionSE
Precision49.41
6
Origin PredictionSE-ORI
Accuracy84.91
5
Emotion ClassificationSE0714
F1 Score37
5
Scientific Information ExtractionSE (full)
Precision (P)51.83
4
Showing 9 of 9 rows