Metric: Out-of-domain (higher is better)
| # | Model↕ | Out-of-domain▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | BERT Large Augmented (single model) | 77.6 | No | BERT: Pre-training of Deep Bidirectional Transfo... | 2018-10-11 | Code |
| 2 | BERT-base finetune (single model) | 74.1 | No | BERT: Pre-training of Deep Bidirectional Transfo... | 2018-10-11 | Code |
| 3 | FlowQA (single model) | 71.8 | No | FlowQA: Grasping Flow in History for Conversatio... | 2018-10-06 | Code |
| 4 | BiDAF++ (single model) | 63.8 | No | A Qualitative Comparison of CoQA, SQuAD 2.0 and ... | 2018-09-27 | Code |
| 5 | DrQA + seq2seq with copy attention (single model) | 60.4 | No | CoQA: A Conversational Question Answering Challe... | 2018-08-21 | Code |
| 6 | Vanilla DrQA (single model) | 47.9 | No | CoQA: A Conversational Question Answering Challe... | 2018-08-21 | Code |