Reinforced Mnemonic Reader for Machine Reading Comprehension
This addresses reading comprehension for AI systems, with incremental improvements over existing attentive readers.
The paper tackles machine reading comprehension by introducing the Reinforced Mnemonic Reader, which uses a reattention mechanism and dynamic-critical reinforcement learning to improve performance, achieving state-of-the-art results on SQuAD and over 6% gains on adversarial datasets.
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.