| Paper | Code | Accuracy | MCC | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Acceptability Judgements via Examining the Topology of Attention Maps | ✓ Link | 88.6 | 0.725 | En-BERT + TDA | 2022-05-19 |
| Acceptability Judgements via Examining the Topology of Attention Maps | ✓ Link | 73 | XLM-R (pre-trained) + TDA | 2022-05-19 | |
| DeBERTa: Decoding-enhanced BERT with Disentangled Attention | ✓ Link | 69.5 | DeBERTa (large) | 2020-06-05 | |
| TinyBERT: Distilling BERT for Natural Language Understanding | ✓ Link | 54 | TinyBERT-6 67M | 2019-09-23 | |
| Synthesizer: Rethinking Self-Attention in Transformer Models | ✓ Link | 53.3 | Synthesizer (R+V) | 2020-05-02 | |
| Acceptability Judgements via Examining the Topology of Attention Maps | ✓ Link | 0.420 | En-BERT (pre-trained) + TDA | 2022-05-19 |