Dissimilar Span Detection on SemEval Task 2 2016 (test)
44.1F1-DiffToken Classification
Evaluation Results
| Method | Links | |
|---|---|---|
| Token ClassificationBackbone=roberta-base, Model Size=125M, Eval. Time=0.102026.03 | 44.1 | |
| LLMModel=Claude 3.5 Sonnet, Model Size=Billions, Eval. Time=39.222026.03 | 38.9 | |
| EmbeddingBackbone=all-mpnet-base-v2, Threshold=0.008, Model Size=109M, Eval. Time=1.132026.03 | 35.2 | |
| EmbeddingBackbone=text-embedding-004, Threshold=0.005, Model Size=Billions, Eval. Time=34.572026.03 | 33.8 | |
| Naive-DSD2026.03 | 30.7 | |
| SHAPBackbone=all-MiniLM-L6-v2, Threshold=0.010, Model Size=22.7M, Eval. Time=4.522026.03 | 30.6 | |
| LIMEBackbone=all-mpnet-base-v2, Threshold=0.001, Model Size=109M, Eval. Time=199.892026.03 | 10.9 | |
| No-DSD2026.03 | 0 |