Problem and method sentence extraction on Abstract dataset
78.77AccuracyContext-enhanced Transformer + Embed-True
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Context-enhanced Transformer + Embed-TrueAugmentation=Embed, Strategy=true-discrimination2026.06 | 78.77 | 75.5 | 73.35 | 73.91 | 66.28 | 68.75 | 75.74 | 84.86 | |
| Context-enhanced Transformer + DependTree FE-TrueAugmentation=DependTree FE, Strategy=true-discrimination2026.06 | 76.09 | 75.65 | 74.14 | 74.33 | 69 | 74.92 | 79.72 | 73.67 | |
| Context-enhanced Transformer + PLM-TrueAugmentation=PLM, Strategy=true-discrimination2026.06 | 75.42 | 75.44 | 73.05 | 73.57 | 67.12 | 73.98 | 79.9 | 73.26 | |
| Context-enhanced Transformer + BackTrans-TrueAugmentation=BackTrans, Strategy=true-discrimination2026.06 | 75.27 | 75.65 | 73.38 | 73.59 | 68.45 | 75.04 | 79.05 | 71.82 | |
| Context-enhanced Transformer + Random-TrueAugmentation=Random, Strategy=true-discrimination2026.06 | 75.18 | 76.21 | 73.33 | 73.94 | 70.18 | 73.29 | 78.28 | 74.04 | |
| Context-enhanced Transformer + TFIDF-TrueAugmentation=TFIDF, Strategy=true-discrimination2026.06 | 75.17 | 75.14 | 73.86 | 73.92 | 68.59 | 74.26 | 78.97 | 73.85 | |
| Context-enhanced Transformer + ChatGPT-TrueAugmentation=ChatGPT, Strategy=true-discrimination2026.06 | 75.02 | 74.67 | 74.04 | 73.58 | 70.02 | 73.16 | 78.61 | 72.52 | |
| Context-enhanced TransformerAugmentation=None2026.06 | 74.85 | 74.75 | 74.02 | 73.45 | 68.68 | 73.37 | 77.95 | 73.79 |