| Linguistic Knowledge as Memory for Recurrent Neural Networks | | 78.6 | | GA+MAGE (32) | 2017-03-07 |
| Gated-Attention Readers for Text Comprehension | ✓ Link | 77.9 | 80.9 | GA Reader | 2016-06-05 |
| A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task | ✓ Link | 77.6 | 79.2 | Attentive + relabling + ensemble | 2016-06-09 |
| Bidirectional Attention Flow for Machine Comprehension | ✓ Link | 76.9 | 79.6 | BiDAF | 2016-11-05 |
| Iterative Alternating Neural Attention for Machine Reading | ✓ Link | 76.1 | | AIA | 2016-06-07 |
| Text Understanding with the Attention Sum Reader Network | ✓ Link | 75.4 | 77.7 | AS Reader (ensemble model) | 2016-03-04 |
| ReasoNet: Learning to Stop Reading in Machine Comprehension | | 74.7 | 76.6 | ReasoNet | 2016-09-17 |
| Attention-over-Attention Neural Networks for Reading Comprehension | ✓ Link | 74.4 | | AoA Reader | 2016-07-15 |
| Natural Language Comprehension with the EpiReader | | 74 | | EpiReader | 2016-06-07 |
| Dynamic Entity Representation with Max-pooling Improves Machine Reading | | 72.9 | | Dynamic Entity Repres. + w2v | 2016-06-01 |
| A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task | ✓ Link | 72.4 | 75.8 | AttentiveReader + bilinear attention | 2016-06-09 |
| Text Understanding with the Attention Sum Reader Network | ✓ Link | 69.5 | 73.9 | AS Reader (single model) | 2016-03-04 |
| Teaching Machines to Read and Comprehend | ✓ Link | 69.4 | | MemNNs (ensemble) | 2015-06-10 |
| A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task | ✓ Link | 67.9 | 68.3 | Classifier | 2016-06-09 |
| Teaching Machines to Read and Comprehend | ✓ Link | 63.8 | 68.0 | Impatient Reader | 2015-06-10 |
| Teaching Machines to Read and Comprehend | ✓ Link | 63 | 69 | Attentive Reader | 2015-06-10 |