Roll call vote prediction (Time-Based)
94.46Balanced AccuracyKALM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| KALMCategory=task agnostic2022.10 | 94.46 | 91.97 | |
| KALMtype=Knowledge-Aware LM2022.10 | 94.46 | 91.97 | |
| Joshi et al.Category=task agnostic2022.10 | 92.63 | 89.31 | |
| Joshi et al.type=Knowledge-Aware LM2022.10 | 92.63 | 89.31 | |
| GreaseLM+Category=task agnostic2022.10 | 91.69 | 87.95 | |
| GreaseLM+type=Knowledge-Aware LM2022.10 | 91.69 | 87.95 | |
| KELMCategory=task agnostic2022.10 | 90.8 | 86.62 | |
| KELMtype=Knowledge-Aware LM2022.10 | 90.8 | 86.62 | |
| RoBERTaCategory=language model, Backbone=roberta-base2022.10 | 90.4 | 84.78 | |
| Pretrained Language Model (BestLM)2022.10 | 90.4 | 85.21 | |
| BARTCategory=language model, Backbone=bart-base2022.10 | 90.25 | 85.21 | |
| PARCategory=task specific2022.10 | 89.92 | — | |
| Task-specific baseline SOTA2022.10 | 89.92 | 84.35 | |
| VoteCategory=task specific2022.10 | 89.76 | 84.35 | |
| LongFormerCategory=language model, Backbone=longformer-base-40962022.10 | 89.32 | 83.42 | |
| ElectraCategory=language model, Backbone=electra-small-discriminator2022.10 | 88.92 | 82.5 | |
| DeBERTaCategory=language model, Backbone=deberta-v3-base2022.10 | 88.59 | 81.38 | |
| GreaseLMCategory=task agnostic2022.10 | 88.21 | 79.73 | |
| GreaseLMtype=Knowledge-Aware LM2022.10 | 88.21 | 79.73 | |
| KnowBERT-W+WCategory=task agnostic2022.10 | 87.07 | 78.42 | |
| KnowBERTtype=Knowledge-Aware LM2022.10 | 87.07 | 78.9 | |
| KnowBERT-WordnetCategory=task agnostic2022.10 | 86.92 | 78.9 | |
| KnowBERT-WikidataCategory=task agnostic2022.10 | 86.45 | 78.21 | |
| ideal-vectorCategory=task specific2022.10 | 81.95 | 75.49 | |
| KGAPCategory=task agnostic2022.10 | 77.9 | 70.81 | |
| KGAPtype=Knowledge-Aware LM2022.10 | 77.9 | 70.81 |