scholarly journals A novel framework for Automatic Chinese Question Generation based on multi-feature neural network model

2018 ◽  
Vol 15 (3) ◽  
pp. 487-499 ◽  
Author(s):  
Hai-Tao Zheng ◽  
Jinxin Han ◽  
Jinyuan Chen ◽  
Arun Sangaiah
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Language Processing ◽  
Neural Network Model ◽  
State Of The Art ◽  
Ranking Methods ◽  
Question Generation ◽  
Human Evaluation ◽  
Automatic Question Generation

Automatic question generation from text or paragraph is a great challenging task which attracts broad attention in natural language processing. Because of the verbose texts and fragile ranking methods, the quality of top generated questions is poor. In this paper, we present a novel framework Automatic Chinese Question Generation (ACQG) to generate questions from text or paragraph. In ACQG, we use an adopted TextRank to extract key sentences and a template-based method to construct questions from key sentences. Then a multi-feature neural network model is built for ranking to obtain the top questions. The automatic evaluation result reveals that the proposed framework outperforms the state-of-the-art systems in terms of perplexity. In human evaluation, questions generated by ACQG rate a higher score.

Automatic question generation based on sentence structure analysis using machine learning approach

2021 ◽  
pp. 1-31
Author(s):  
Miroslav Blšták ◽  
Viera Rozinajová
Keyword(s):  
Machine Learning ◽  
Natural Language ◽  
Language Processing ◽  
State Of The Art ◽  
Sentence Structure ◽  
Question Generation ◽  
Transformation Rules ◽  
Input Text ◽  
Automatic Question Generation

Abstract Automatic question generation is one of the most challenging tasks of Natural Language Processing. It requires “bidirectional” language processing: first, the system has to understand the input text (Natural Language Understanding), and it then has to generate questions also in the form of text (Natural Language Generation). In this article, we introduce our framework for generating the factual questions from unstructured text in the English language. It uses a combination of traditional linguistic approaches based on sentence patterns with several machine learning methods. We first obtain lexical, syntactic and semantic information from an input text, and we then construct a hierarchical set of patterns for each sentence. The set of features is extracted from the patterns, and it is then used for automated learning of new transformation rules. Our learning process is totally data-driven because the transformation rules are obtained from a set of initial sentence–question pairs. The advantages of this approach lie in a simple expansion of new transformation rules which allows us to generate various types of questions and also in the continuous improvement of the system by reinforcement learning. The framework also includes a question evaluation module which estimates the quality of generated questions. It serves as a filter for selecting the best questions and eliminating incorrect ones or duplicates. We have performed several experiments to evaluate the correctness of generated questions, and we have also compared our system with several state-of-the-art systems. Our results indicate that the quality of generated questions outperforms the state-of-the-art systems and our questions are also comparable to questions created by humans. We have also created and published an interface with all created data sets and evaluated questions, so it is possible to follow up on our work.

scholarly journals Contribution to image restoration using a neural network model

2002 ◽  
Vol Volume 1, 2002 ◽  
Author(s):  
Karim Achour ◽  
Nadia Zenati ◽  
Oualid Djekoune
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
Network Model ◽  
Neural Network Model ◽  
Hopfield Neural Network ◽  
Optimization Method ◽  
Nous Proposons ◽  
International Audience ◽  
High Level

International audience The reduction of the blur and the noise is an important task in image processing. Indeed, these two types of degradation are some undesirable components during some high level treatments. In this paper, we propose an optimization method based on neural network model for the regularized image restoration. We used in this application a modified Hopfield neural network. We propose two algorithms using the modified Hopfield neural network with two updating modes : the algorithm with a sequential updates and the algorithm with the n-simultaneous updates. The quality of the obtained result attests the efficiency of the proposed method when applied on several images degraded with blur and noise. La réduction du bruit et du flou est une tâche très importante en traitement d'images. En effet, ces deux types de dégradations sont des composantes indésirables lors des traitements de haut niveau. Dans cet article, nous proposons une méthode d'optimisation basée sur les réseaux de neurones pour résoudre le problème de restauration d'images floues-bruitées. Le réseau de neurones utilisé est le réseau de « Hopfield ». Nous proposons deux algorithmes utilisant deux modes de mise à jour: Un algorithme avec un mode de mise à jour séquentiel et un algorithme avec un mode de mise à jour n-simultanée. L'efficacité de la méthode mise en œuvre a été testée sur divers types d'images dégradées.

scholarly journals PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution

2022 ◽  
Vol 8 ◽  
pp. e842
Author(s):  
Jungwoo Shin ◽  
HyunJin Kim
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
State Of The Art ◽  
Classification Performance ◽  
Performance Degradation ◽  
Critical Problem ◽  
Hardware Costs ◽  
Performance Enhancing

In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performance degradation is the most critical problem in BNN models. Our PresB-Net combines several state-of-the-art BNN structures including the learnable activation with additional trainable parameters and shuffled grouped convolution. Notably, we propose a new normalization approach, which reduces the imbalance between the shuffled groups occurring in shuffled grouped convolutions. Besides, the proposed normalization approach helps gradient convergence so that the unstableness of the learning can be amortized when applying the learnable activation. Our novel BNN model enhances the classification performance compared with other existing BNN models. Notably, the proposed PresB-Net-18 achieves 73.84% Top-1 inference accuracy for the CIFAR-100 dataset, outperforming other existing counterparts.

scholarly journals Generating Medical Assessments Using a Neural Network Model: Algorithm Development and Validation (Preprint)

2019 ◽  
Author(s):  
Baotian Hu ◽  
Adarsha Bajracharya ◽  
Hong Yu
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Language Processing ◽  
Neural Network Model ◽  
Objective Assessment ◽  
Processing System ◽  
Clinical Decision ◽  
Medical Assessment ◽  
Clinical Diagnoses ◽  
Electronic Health

BACKGROUND Since its inception, artificial intelligence has aimed to use computers to help make clinical diagnoses. Evidence-based medical reasoning is important for patient care. Inferring clinical diagnoses is a crucial step during the patient encounter. Previous works mainly used expert systems or machine learning–based methods to predict the International Classification of Diseases - Clinical Modification codes based on electronic health records. We report an alternative approach: inference of clinical diagnoses from patients’ reported symptoms and physicians’ clinical observations. OBJECTIVE We aimed to report a natural language processing system for generating medical assessments based on patient information described in the electronic health record (EHR) notes. METHODS We processed EHR notes into the Subjective, Objective, Assessment, and Plan sections. We trained a neural network model for medical assessment generation (N2MAG). Our N2MAG is an innovative deep neural model that uses the Subjective and Objective sections of an EHR note to automatically generate an “expert-like” assessment of the patient. N2MAG can be trained in an end-to-end fashion and does not require feature engineering and external knowledge resources. RESULTS We evaluated N2MAG and the baseline models both quantitatively and qualitatively. Evaluated by both the Recall-Oriented Understudy for Gisting Evaluation metrics and domain experts, our results show that N2MAG outperformed the existing state-of-the-art baseline models. CONCLUSIONS N2MAG could generate a medical assessment from the Subject and Objective section descriptions in EHR notes. Future work will assess its potential for providing clinical decision support.

scholarly journals DeepSeqPanII: an interpretable recurrent neural network model with attention mechanism for peptide-HLA class II binding prediction

2020 ◽  
Author(s):  
ZHONGHAO LIU ◽  
Jing Jin ◽  
Yuxin Cui ◽  
Zheng Xiong ◽  
Alireza Nasiri ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Network Structure ◽  
State Of The Art ◽  
Class Ii ◽  
Hla Class Ii ◽  
Binding Prediction ◽  
Neural Network Structure ◽  
Art Performance

Abstract Background: Human leukocyte antigen (HLA) complex molecules play an essential role in immune interactions by presenting peptides on the cell surface to T cells. With significant progress in deep learning, a series of neural network based models have been proposed and demonstrated with their good performances for peptide-HLA class I binding prediction. However, there still lack effective binding prediction models for HLA class II protein binding with peptides due to its inherent challenges. In this work, we present a novel sequence-based pan-specific neural network structure, DeepSeaPanII, for peptide-HLA class II binding prediction. Compared with existing pan-specific models, our model is an end-to-end neural network model without the need for pre- or post-processing on input samples. Results: The leave-one-allele-out cross validation and benchmark evaluation results show that our proposed network model achieved state-of-the-art performance in HLA-II peptide binding. Besides state-of-the-art performance in binding affinity prediction, DeepSeqPanII can also extract biological insight on the binding mechanism over the peptide and HLA sequences by its attention mechanism based binding core prediction capability. Conclusions: In this work, we present a novel neural network structure for peptide-HLA class II binding prediction. It has state-of-the-art performance and could display insightful information it learned benefiting from attention module we carefully designed. Without requiring additional data, this structure could be applied to other related sequence problems. The source code and trained models are freely available at https://github.com/pcpLiu/DeepSeqPanII.

Sign in / Sign up

Export Citation Format

Share Document