Question Matching on BQ Corpus (dev)
86.7AccuracyELECTRA-large
Evaluation results
| Method | Links | |
|---|---|---|
| ELECTRA-largemodel size=large2020.04 | 86.7 | |
| ERNIE 2.0Model Version=ERNIE 2.0, Model Scale=LARGE2019.07 | 86.5 | |
| ChineseBERTModel Scale=Large, Pre-trained on extended data=false2021.06 | 86.5 | |
| ERNIE 2.0Model Version=ERNIE 2.0, Model Scale=BASE2019.07 | 86.4 | |
| BERT-wwm-extmodel size=base2020.04 | 86.4 | |
| BERTModel Scale=Base, Pre-trained on extended data=true2021.06 | 86.4 | |
| ChineseBERTModel Scale=Base, Pre-trained on extended data=false2021.06 | 86.4 | |
| ROBERTa-wwm-ext-largemodel size=large2020.04 | 86.3 | |
| ERNIEModel Scale=Base, Pre-trained on extended data=false2021.06 | 86.3 | |
| RoBERTaModel Scale=Large, Pre-trained on extended data=true2021.06 | 86.3 | |
| MacBERT-largemodel size=large2020.04 | 86.2 | |
| MacBERTModel Scale=Large, Pre-trained on extended data=false2021.06 | 86.2 | |
| ERNIE 1.0Model Version=ERNIE 1.0, Model Scale=BASE2019.07 | 86.1 | |
| BERT-wwmmodel size=base2020.04 | 86.1 | |
| BERTModel Scale=Base, Pre-trained on extended data=false2021.06 | 86.1 | |
| BERTmodel size=base2020.04 | 86 | |
| ROBERTa-wwm-extmodel size=base2020.04 | 86 | |
| MacBERT-basemodel size=base2020.04 | 86 | |
| RoBERTaModel Scale=Base, Pre-trained on extended data=true2021.06 | 86 | |
| MacBERTModel Scale=Base, Pre-trained on extended data=false2021.06 | 86 | |
| BERTModel Version=BERT, Model Scale=BASE2019.07 | 85.9 | |
| ELECTRA-basemodel size=base2020.04 | 84.8 |