scholarly journals Reinforced Mnemonic Reader for Machine Reading Comprehension

2018 ◽  
Author(s):  
Minghao Hu ◽  
Yuxing Peng ◽  
Zhen Huang ◽  
Xipeng Qiu ◽  
Furu Wei ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Reinforcement Learning ◽  
Question Answering ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Optimization Approach ◽  
Exact Match ◽  
Machine Reading

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.

scholarly journals Synthetic Experiences for Accelerating DQN Performance in Discrete Non-Deterministic Environments

Algorithms ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 226
Author(s):  
Wenzel Pilar von Pilchau ◽  
Anthony Stein ◽  
Jörg Hähner
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Weighted Average ◽  
Up States ◽  
Experience Replay

State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We propose a method called Interpolated Experience Replay that uses stored (real) transitions to create synthetic ones to assist the learner. In this first approach to this field, we limit ourselves to discrete and non-deterministic environments and use a simple equally weighted average of the reward in combination with observed follow-up states. We could demonstrate a significantly improved overall mean average in comparison to a DQN network with vanilla Experience Replay on the discrete and non-deterministic FrozenLake8x8-v0 environment.

scholarly journals Translucent Answer Predictions in Multi-Hop Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7700-7707
Author(s):  
G P Shrivatsa Bhargav ◽  
Michael Glass ◽  
Dinesh Garg ◽  
Shirish Shevade ◽  
Saswati Dana ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Local Context ◽  
The Novel ◽  
Loose Coupling ◽  
Loosely Coupled ◽  
Neural Architecture ◽  
Coupled Networks ◽  
Novel Design

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

scholarly journals Towards Reading Comprehension for Long Documents

2018 ◽  
Author(s):  
Yuanxing Zhang ◽  
Yangbin Zhang ◽  
Kaigui Bian ◽  
Xiaoming Li
Keyword(s):  
Reading Comprehension ◽  
Language Comprehension ◽  
Exact Match ◽  
Attention Model ◽  
Comprehension Task ◽  
Proposed Model ◽  
Short Span ◽  
Machine Reading ◽  
The Relationship

Machine reading comprehension has gained attention from both industry and academia. It is a very challenging task that involves various domains such as language comprehension, knowledge inference, summarization, etc. Previous studies mainly focus on reading comprehension on short paragraphs, and these approaches fail to perform well on the documents. In this paper, we propose a hierarchical match attention model to instruct the machine to extract answers from a specific short span of passages for the long document reading comprehension (LDRC) task. The model takes advantages from hierarchical-LSTM to learn the paragraph-level representation, and implements the match mechanism (i.e., quantifying the relationship between two contexts) to find the most appropriate paragraph that includes the hint of answers. Then the task can be decoupled into reading comprehension task for short paragraph, such that the answer can be produced. Experiments on the modified SQuAD dataset show that our proposed model outperforms existing reading comprehension models by at least 20% regarding exact match (EM), F1 and the proportion of identified paragraphs which are exactly the short paragraphs where the original answers locate.

scholarly journals Deterministic Value-Policy Gradients

2020 ◽  
Vol 34 (04) ◽  
pp. 3316-3323
Author(s):  
Qingpeng Cai ◽  
Ling Pan ◽  
Pingzhong Tang
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Infinite Horizon ◽  
Gradient Algorithm ◽  
Continuous Control ◽  
Model Bias ◽  
Model Free ◽  
Policy Gradient ◽  
Analytical Gradients

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of deep reinforcement learning algorithms. Previous works consider deterministic value gradients with the finite horizon, but it is too myopic compared with infinite horizon. We firstly give a theoretical guarantee of the existence of the value gradients in this infinite setting. Based on this theoretical guarantee, we propose a class of the deterministic value gradient algorithm (DVG) with infinite horizon, and different rollout steps of the analytical gradients by the learned model trade off between the variance of the value gradients and the model bias. Furthermore, to better combine the model-based deterministic value gradient estimators with the model-free deterministic policy gradient estimator, we propose the deterministic value-policy gradient (DVPG) algorithm. We finally conduct extensive experiments comparing DVPG with state-of-the-art methods on several standard continuous control benchmarks. Results demonstrate that DVPG substantially outperforms other baselines.

scholarly journals Analyzing the Effect of Masking Length Distribution of MLM: An Evaluation Framework and Case Study on Chinese MRC Datasets

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Changchang Zeng ◽  
Shaobo Li
Keyword(s):  
Reading Comprehension ◽  
Language Processing ◽  
Question Answering ◽  
Multiple Choice ◽  
Length Distribution ◽  
Research Field ◽  
Evaluation Framework ◽  
Language Models ◽  
Training Objective ◽  
Machine Reading

Machine reading comprehension (MRC) is a challenging natural language processing (NLP) task. It has a wide application potential in the fields of question answering robots, human-computer interactions in mobile virtual reality systems, etc. Recently, the emergence of pretrained models (PTMs) has brought this research field into a new era, in which the training objective plays a key role. The masked language model (MLM) is a self-supervised training objective widely used in various PTMs. With the development of training objectives, many variants of MLM have been proposed, such as whole word masking, entity masking, phrase masking, and span masking. In different MLMs, the length of the masked tokens is different. Similarly, in different machine reading comprehension tasks, the length of the answer is also different, and the answer is often a word, phrase, or sentence. Thus, in MRC tasks with different answer lengths, whether the length of MLM is related to performance is a question worth studying. If this hypothesis is true, it can guide us on how to pretrain the MLM with a relatively suitable mask length distribution for MRC tasks. In this paper, we try to uncover how much of MLM’s success in the machine reading comprehension tasks comes from the correlation between masking length distribution and answer length in the MRC dataset. In order to address this issue, herein, (1) we propose four MRC tasks with different answer length distributions, namely, the short span extraction task, long span extraction task, short multiple-choice cloze task, and long multiple-choice cloze task; (2) four Chinese MRC datasets are created for these tasks; (3) we also have pretrained four masked language models according to the answer length distributions of these datasets; and (4) ablation experiments are conducted on the datasets to verify our hypothesis. The experimental results demonstrate that our hypothesis is true. On four different machine reading comprehension datasets, the performance of the model with correlation length distribution surpasses the model without correlation.

scholarly journals Importance of the Single-Span Task Formulation to Extractive Question-answering

2020 ◽  
Author(s):  
Marie-Anne Xu ◽  
Rahul Khanna
Keyword(s):  
Reading Comprehension ◽  
Future Development ◽  
Recent Progress ◽  
Question Answering ◽  
Span Task ◽  
Consistent Performance ◽  
Machine Reading

Recent progress in machine reading comprehension and question-answering has allowed machines to reach and even surpass human question-answering. However, the majority of these questions have only one answer, and more substantial testing on questions with multiple answers, or multi-span questions, has not yet been applied. Thus, we introduce a newly compiled dataset consisting of questions with multiple answers that originate from previously existing datasets. In addition, we run BERT-based models pre-trained for question-answering on our constructed dataset to evaluate their reading comprehension abilities. Among the three of BERT-based models we ran, RoBERTa exhibits the highest consistent performance, regardless of size. We find that all our models perform similarly on this new, multi-span dataset (21.492% F1) compared to the single-span source datasets (~33.36% F1). While the models tested on the source datasets were slightly fine-tuned, performance is similar enough to judge that task formulation does not drastically affect question-answering abilities. Our evaluations indicate that these models are indeed capable of adjusting to answer questions that require multiple answers. We hope that our findings will assist future development in questionanswering and improve existing question-answering products and methods.

scholarly journals Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

2019 ◽  
Vol 33 ◽  
pp. 6276-6283 ◽  
Author(s):  
Zhipeng Chen ◽  
Yiming Cui ◽  
Wentao Ma ◽  
Shijin Wang ◽  
Guoping Hu
Keyword(s):  
Reading Comprehension ◽  
Mutual Information ◽  
Spatial Attention ◽  
State Of The Art ◽  
Multiple Choice ◽  
Multiple Choice Questions ◽  
Attention Model ◽  
Novel Approach ◽  
Proposed Model ◽  
Machine Reading

Machine Reading Comprehension (MRC) with multiplechoice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of- the-art systems on both RACE and SemEval-2018 Task11 datasets.

scholarly journals Rception: Wide and Deep Interaction Networks for Machine Reading Comprehension (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13987-13988
Author(s):  
Xuanyu Zhang ◽  
Zhichun Wang
Keyword(s):  
Neural Networks ◽  
Reading Comprehension ◽  
Convolutional Neural Networks ◽  
Recurrent Neural Networks ◽  
Question Answering ◽  
Local Information ◽  
Interaction Networks ◽  
Layer By Layer ◽  
Global Context ◽  
Machine Reading

Most of models for machine reading comprehension (MRC) usually focus on recurrent neural networks (RNNs) and attention mechanism, though convolutional neural networks (CNNs) are also involved for time efficiency. However, little attention has been paid to leverage CNNs and RNNs in MRC. For a deeper understanding, humans sometimes need local information for short phrases, sometimes need global context for long passages. In this paper, we propose a novel architecture, i.e., Rception, to capture and leverage both local deep information and global wide context. It fuses different kinds of networks and hyper-parameters horizontally rather than simply stacking them layer by layer vertically. Experiments on the Stanford Question Answering Dataset (SQuAD) show that our proposed architecture achieves good performance.

scholarly journals UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension

2021 ◽  
Author(s):  
Samreen Ahmed ◽  
shakeel khoja
Keyword(s):  
Reading Comprehension ◽  
Machine Translation ◽  
Large Scale ◽  
Question Answering ◽  
Training Data ◽  
Significant Progress ◽  
Rule Based ◽  
Low Resource ◽  
Machine Reading ◽  
Answer Format

<p>In recent years, low-resource Machine Reading Comprehension (MRC) has made significant progress, with models getting remarkable performance on various language datasets. However, none of these models have been customized for the Urdu language. This work explores the semi-automated creation of the Urdu Question Answering Dataset (UQuAD1.0) by combining machine-translated SQuAD with human-generated samples derived from Wikipedia articles and Urdu RC worksheets from Cambridge O-level books. UQuAD1.0 is a large-scale Urdu dataset intended for extractive machine reading comprehension tasks consisting of 49k question Answers pairs in question, passage, and answer format. In UQuAD1.0, 45000 pairs of QA were generated by machine translation of the original SQuAD1.0 and approximately 4000 pairs via crowdsourcing. In this study, we used two types of MRC models: rule-based baseline and advanced Transformer-based models. However, we have discovered that the latter outperforms the others; thus, we have decided to concentrate solely on Transformer-based architectures. Using XLMRoBERTa and multi-lingual BERT, we acquire an F<sub>1</sub> score of 0.66 and 0.63, respectively.</p>

scholarly journals Universal Reinforcement Learning Algorithms: Survey and Experiments

2017 ◽  
Author(s):  
John Aslanides ◽  
Jan Leike ◽  
Marcus Hutter
Keyword(s):  
Reinforcement Learning ◽  
Open Source ◽  
Markov Decision Process ◽  
Decision Process ◽  
Empirical Investigation ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Markov Decision ◽  
Reference Implementation ◽  
Partially Observable

Many state-of-the-art reinforcement learning (RL) algorithms typically assume that the environment is an ergodic Markov Decision Process (MDP). In contrast, the field of universal reinforcement learning (URL) is concerned with algorithms that make as few assumptions as possible about the environment. The universal Bayesian agent AIXI and a family of related URL algorithms have been developed in this setting. While numerous theoretical optimality results have been proven for these agents, there has been no empirical investigation of their behavior to date. We present a short and accessible survey of these URL algorithms under a unified notation and framework, along with results of some experiments that qualitatively illustrate some properties of the resulting policies, and their relative performance on partially-observable gridworld environments. We also present an open- source reference implementation of the algorithms which we hope will facilitate further understanding of, and experimentation with, these ideas.

Sign in / Sign up

Export Citation Format

Share Document