Question Classification on TREC 50 (test)
97.2AccuracyRules
Evaluation results
| Method | Links | |
|---|---|---|
| Rules2017.08 | 97.2 | |
| RulesArchitecture=Rules2018.05 | 97.2 | |
| FFTModel=DeBERTa v2 XXL [24]2026.06 | 91.99 | |
| cLAModel=DeBERTa v2 XXL [24], Adapter rank=162026.06 | 91.73 | |
| SVMsource=Van-Tu and Anh-Cuong, 20162017.08 | 91.6 | |
| RulesUHC2017.08 | 90.8 | |
| RulesUHCArchitecture=RulesUHC2018.05 | 90.8 | |
| BCN+Char+CoVeembeddings=GloVe, character n-gram, CoVe2017.08 | 90.2 | |
| BCN+Char+CoVeArchitecture=BCN, Embeddings=Char, CoVe2018.05 | 90.2 | |
| BCN with SuBiLSTM+CoVeArchitecture=BCN, Encoder=SuBiLSTM, Embeddings=CoVe2018.05 | 90.2 | |
| BCN with SuBiLSTM-Tied+CoVeArchitecture=BCN, Encoder=SuBiLSTM-Tied, Embeddings=CoVe2018.05 | 90.2 | |
| FFTModel=DeBERTa v3 Base [23]2026.06 | 90.15 | |
| BCN with BiLSTM+CoVeArchitecture=BCN, Encoder=BiLSTM, Embeddings=CoVe2018.05 | 90 | |
| BCN with BiLSTMArchitecture=BCN, Encoder=BiLSTM2018.05 | 89.8 | |
| BCN with SuBiLSTMArchitecture=BCN, Encoder=SuBiLSTM2018.05 | 89.8 | |
| BCN with 2-layer BiLSTMArchitecture=BCN, Encoder=2-layer BiLSTM2018.05 | 89.4 | |
| BCN with SuBiLSTM-TiedArchitecture=BCN, Encoder=SuBiLSTM-Tied2018.05 | 89.4 | |
| SNOW2017.08 | 89.3 | |
| BCN with 2-layer BiLSTM+CoVeArchitecture=BCN, Encoder=2-layer BiLSTM, Embeddings=CoVe2018.05 | 89.2 | |
| SVMsource=Loni et al., 20112017.08 | 89 | |
| cLAModel=DeBERTa v3 Base [23], Adapter rank=162026.06 | 86.04 |