Question Answering on NarrativeQA
Metric: BLEU-4 (higher is better)
Metric: BLEU-4 (higher is better)
| # | Model↕ | BLEU-4▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Masque (NarrativeQA + MS MARCO) | 30.43 | Yes | Multi-style Generative Reading Comprehension | 2019-01-08 | - |
| 2 | DecaProp | 27.61 | No | Densely Connected Attention Propagation for Read... | 2018-11-10 | Code |
| 3 | ConZNet | 22.49 | No | - | - | - |
| 4 | MHPGM + NOIC | 21.07 | No | Commonsense for Generative Multi-Hop Question An... | 2018-09-17 | Code |
| 5 | Masque (NarrativeQA only) | 20.98 | No | Multi-style Generative Reading Comprehension | 2019-01-08 | - |
| 6 | BiAttention + DCU-LSTM | 19.79 | No | - | - | - |
| 7 | BiDAF | 15.69 | No | Bidirectional Attention Flow for Machine Compreh... | 2016-11-05 | Code |
| 8 | FiD+Distil | 7.5 | No | Distilling Knowledge from Reader to Retriever fo... | 2020-12-08 | Code |