Reinforced Mnemonic Reader for Machine Reading Comprehension

By Minghao Hu, Yuxing Peng, Zhen Huang, Xipeng Qiu, Furu Wei, M. Zhou. 2017

216 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019, background): “Table 2 shows top leaderboard entries as well as results from top published systems (Seo et al., 2017; Clark and Gardner, 2018; Peters et al., 2018a; Hu et al., 2018).”
U-Net: Machine Reading Comprehension with Unanswerable Questions (2018, methodology): “…Currently, end-to-end neural network models have achieved great successes for machine reading comprehension (Seo et al. 2016; Kumar et al. 2015; Sukhbaatar et al. 2015; Cui et al. 2016; Xiong, Zhong, and Socher 2016; Dhingra et al. 2016; Shen et al. 2016; Hu et al. 2017; Wang, Yan, and Wu 2018).”
The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “…does not hold for question answering in general, so recent models for SQuAD are not necessarily general question answering models [Yu et al., 2018a, Hu et al., 2018, Wang et al., 2017a, Liu et al., 2017b, Huang et al., 2017, Xiong et al., 2018, Liu et al., 2017a, Pan et al., 2017, Salant and…”
The Effect of Natural Distribution Shift on Question Answering Models (2020, neutral): “Reinforced Mnemonic Reader (Ensemble) (Hu et al., 2018) https://worksheets.”
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (2019, methodology): “Neural reading models Previous neural reading models, such as BiDAF (Seo et al., 2017), R-Net (Wang et al., 2017), QANet (Yu et al., 2018), Reinforced Mreader (Hu et al., 2018), are usually designed to extract a continuous span of text as the answer.”
Stochastic Answer Networks for Machine Reading Comprehension (2017, background): “It is simple yet efﬁcient and can be trained using the classical back-propagation algorithm, thus it is adopted by most of systems (Chen et al., 2016; Seo et al., 2016; Wang et al., 2017; Liu et al., 2017; Chen et al., 2017; Weissenborn et al., 2017; Hu et al., 2017).”
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension (2017, background): “Test Set Single Model EM / F1 LR Baseline (Rajpurkar et al., 2016) 40.4 / 51.0 Match-LSTM (Wang & Jiang, 2016) 64.7 / 73.7 BiDAF (Seo et al., 2017) 68.0 / 77.3 SEDT (Liu et al., 2017) 68.2 / 77.5 RaSoR (Lee et al., 2016) 70.8 / 78.7 DrQA (Chen et al., 2017a) 70.7 / 79.4 ReasoNet (Shen et al., 2017) ”
Cognitive Graph for Multi-Hop Reading Comprehension at Scale (2019, background): “Improvements are made to enhance retrieval by heuristic sampling (Clark and Gardner, 2018) or reinforcement learning (Hu et al., 2018; Wang et al., 2018a), while for complex reasoning, necessary revisits to the framework are neglected.”
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (2019, background): “…dataset, various neural network approaches have been proposed and made a big advancement in this area (Kadlec et al., 2016; Cui et al., 2017; Dhingra et al., 2017; Wang and Jiang, 2016; Xiong et al., 2016; Liu et al., 2017; Wang et al., 2017; Hu et al., 2018; Wang et al., 2018; Yu et al., 2018).”
Multi-Mention Learning for Reading Comprehension with Neural Cascades (2017, methodology): “Surprisingly, we outperform approaches which use multi-layer recurrent pointer networks with specialized memories (Chen et al., 2017b; Hu et al., 2017) 6 .”
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA (2019, background): “They report that the performances of state-of-the-art QA models (Seo et al., 2017; Hu et al., 2018; Huang et al., 2018) drop signiﬁcantly when evaluated on the adversarial data.”
Are Red Roses Red? Evaluating Consistency of Question-Answering Models (2019, methodology): “For SQuAD, we evaluate bidaf (Seo et al., 2017), bidaf with ELMO embeddings ( bidaf+e ; Peters et al., 2018), rnet (Wang et al., 2017), and Mnemonic Reader ( mnem ; Hu et al., 2018).”
Read + Verify: Machine Reading Comprehension with Unanswerable Questions (2018, methodology): “We use the Reinforced Mnemonic Reader (RMR) (Hu et al., 2018a), one of the state-ofthe-art reading comprehension models on the SQuAD 1.”
Cross-Lingual Transfer Learning for Question Answering (2019, background): “Question answering (QA) has drawn much attention in the past few years, and end-to-end deep learning has demonstrated promising performance on QA (Yu et al., 2018; Xiong et al., 2016; Seo et al., 2016; Huang et al., 2017; Wang et al., 2018; Liu et al., 2017; Hu et al., 2017; Wang et al., 2017).”
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model (2019, background): “…al., 2016; Rajpurkar et al., 2016; Nguyen et al., 2016; Trischler et al., 2017; Joshi et al., 2017; Rajpurkar et al., 2018) have nourished the development of numerous powerful and diverse RC models (Seo et al., 2016; Hu et al., 2018; Wang et al., 2017; Clark and Gardner, 2018; Huang et al., 2017).”
HEAD-QA: A Healthcare Dataset for Complex Reasoning (2019, methodology): “This is the case of popular English datasets such as bAbI (Weston et al., 2015) or SQuAD (Ra-jpurkar et al., 2016, 2018), where some systems achieve near human-level performance (Hu et al., 2018; Xiong et al., 2017) and often surface-level knowledge sufﬁces to answer.”
Densely Connected Attention Propagation for Reading Comprehension (2018, background): “…[Xiong et al., 2016, 2017], R-NET [Wang et al., 2017c], DrQA [Chen et al., 2017], AoA Reader [Cui et al., 2016], Reinforced Mnemonic Reader [Hu et al., 2017], ReasoNet [Shen et al., 2017], AMANDA [Kundu and Ng, 2018], R 3 Reinforced Reader Ranker [Wang et al., 2017a] and QANet [Yu et al.,…”