Papers › Reinforced Mnemonic Reader for Machine Reading Comprehension
Reinforced Mnemonic Reader for Machine Reading Comprehension
Minghao Hu, Yuxing Peng, Zhen Huang, Xipeng Qiu, Furu Wei, Ming Zhou
In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more acceptable answer so as to address the convergence suppression problem occurred in traditional reinforcement learning algorithms. Extensive experiments on the Stanford Question Answering Dataset (SQuAD) show that our model achieves state-of-the-art results. Meanwhile, our model outperforms previous systems by over 6% in terms of both Exact Match and F1 metrics on two adversarial SQuAD datasets.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Question Answering | SQuAD1.1 | Reinforced Mnemonic Reader (ensemble model) | EM | 82.283 | #45 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Reinforced Mnemonic Reader (ensemble model) | F1 | 88.533 | #45 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Reinforced Mnemonic Reader (single model) | EM | 79.545 | #73 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Reinforced Mnemonic Reader (single model) | F1 | 86.654 | #73 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Mnemonic Reader (ensemble) | EM | 74.268 | #129 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Mnemonic Reader (ensemble) | F1 | 82.371 | #129 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Mnemonic Reader (single model) | EM | 70.995 | #154 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 | Mnemonic Reader (single model) | F1 | 80.146 | #154 of 213 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 dev | R.M-Reader (single) | EM | 78.9 | #17 of 55 | Archive leaderboard | report |
| Question Answering | SQuAD1.1 dev | R.M-Reader (single) | F1 | 86.3 | #17 of 55 | Archive leaderboard | report |
| Question Answering | TriviaQA | Mnemonic Reader | EM | 46.94 | #45 of 56 | Archive leaderboard | report |
| Question Answering | TriviaQA | Mnemonic Reader | F1 | 52.85 | #45 of 56 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections