Metric: METEOR (higher is better)
| # | Model↕ | METEOR▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Masque (NarrativeQA + MS MARCO) | 26.13 | Yes | Multi-style Generative Reading Comprehension | 2019-01-08 | - |
| 2 | Masque (NarrativeQA only) | 21.95 | No | Multi-style Generative Reading Comprehension | 2019-01-08 | - |
| 3 | DecaProp | 21.8 | No | Densely Connected Attention Propagation for Read... | 2018-11-10 | Code |
| 4 | ConZNet | 19.24 | No | - | - | - |
| 5 | MHPGM + NOIC | 19.03 | No | Commonsense for Generative Multi-Hop Question An... | 2018-09-17 | Code |
| 6 | BiAttention + DCU-LSTM | 17.87 | No | - | - | - |
| 7 | BiDAF | 15.68 | No | Bidirectional Attention Flow for Machine Compreh... | 2016-11-05 | Code |
| 8 | FiD+Distil | 11.1 | No | Distilling Knowledge from Reader to Retriever fo... | 2020-12-08 | Code |