Ig Nobel Winners Retrieval on Ig-Nobel (test)
90.3AccuracySciBERT^f
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SciBERT^fcomponents=SciBERT + paper features embedding concatenation2021.06 | 90.3 | 92.1 | 88.2 | |
| BERT^fcomponents=BERT + paper features embedding concatenation2021.06 | 90.3 | 92.1 | 88.2 | |
| Iggy2021.06 | 88.4 | 91.3 | 84.8 | |
| SciBERTtraining_mode=fine-tuned2021.06 | 88.2 | 90.9 | 84.8 | |
| BERTtraining_mode=fine-tuned2021.06 | 86.3 | 90.5 | 81 | |
| LRmodel_type=Logistic Regression, input=Bag of Words (BoW)2021.06 | 76.5 | 75.5 | 78.7 | |
| RFmodel_type=Random Forest, input=Bag of Words (BoW)2021.06 | 71.3 | 70.8 | 72.5 |