Neural Information Processing

Name: Neural Information Processing | 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part I
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part I

Haiqin Yang Kitsuchart Pasupa Andrew Chi-Sing Leung James T. Kwok Jonathan H. Chan Irwin King(Herausgeber*in)

Springer (Verlag)

Erschienen am 18. November 2020

XXVI, 813 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-030-63830-6 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents - Part I
Human-Computer Interaction
A Genetic Feature Selection Based Two-Stream Neural Network for Anger Veracity Recognition
1 Introduction
2 Method
2.1 Dataset
2.2 Network Architecture
2.3 Two-Stream Architecture
2.4 Data Pre-processing and Feature Selection
3 Experiments and Discussions
3.1 Experiment Settings
3.2 Baseline Model
3.3 Experiments on GFS and Two-Stream Architecture
3.4 Discussion
4 Conclusion and Future Work
References
An Efficient Joint Training Framework for Robust Small-Footprint Keyword Spotting
1 Introduction
2 System Description
2.1 Masking-Based Speech Enhancement Method
2.2 Feature Transformation Block
2.3 Keyword Spotting System
3 Experiments and Results
3.1 Experimental Settings
3.2 Results
4 Conclusions
References
Hierarchical Interactive Matching Network for Multi-turn Response Selection in Retrieval-Based Chatbots
1 Introduction
2 Related Work
3 Hierarchical Interactive Matching Network
3.1 Task Description
3.2 Model Overview
3.3 Multi-level Attention Representation
3.4 Two-Level Hierarchical Interactive Matching
3.5 Aggregation
4 Experiments
4.1 Dataset
4.2 Evaluation Metric
4.3 Baseline Models
4.4 Experiment Settings
4.5 Experiment Results
4.6 Discussions
5 Conclusion
References
Investigation of Effectively Synthesizing Code-Switched Speech Using Highly Imbalanced Mix-Lingual Data
1 Introduction
2 Related Work
2.1 Data Sets for the CS TTS
2.2 Text Representation for CS TTS
3 Proposed Method
3.1 General Framework
3.2 CS Front-End
3.3 Synthesis Module
4 Data Description
5 Experiments
5.1 Input Representations
5.2 Experimental Setup
5.3 Experimental Results
6 Conclusion
References
Image Processing and Computer Vision
A Feature Fusion Network for Multi-modal Mesoscale Eddy Detection
1 Introduction
2 Related Work
2.1 Non-deep Learning Algorithms
2.2 Deep Learning Algorithms
3 Methodology
3.1 FusionNet
3.2 The Loss Function
4 Experiments
4.1 The Multi-modal Dataset
4.2 Experimental Results
5 Conclusion
References
A Hybrid Self-Attention Model for Pedestrians Detection
1 Introduction
2 Related Work
2.1 Pedestrian Detection
2.2 Attention Mechanism
3 Proposed Method
3.1 Revisiting the CSP Detector
3.2 Channel Attention
3.3 Spatial Attention
3.4 Hybrid Attention Fusion Strategy
4 Experiments
4.1 Dataset and Evaluation Metrics
4.2 Ablation Study
4.3 Comparison with State of the Arts
5 Conclusion
References
DF-PLSTM-FCN: A Method for Unmanned Driving Based on Dual-Fusions and Parallel LSTM-FCN
1 Introduction
2 Related Work
3 DF-PLSTM-FCN
3.1 Driving Model
3.2 Network Structure
3.3 Feature Fusion
3.4 Decision Fusion
3.5 Model Evaluation
4 Experiment
4.1 Dataset
4.2 Parameter Setting
4.3 Experiment Analysis
4.4 Evaluation Index
5 Conclusion
References
A Modified Joint Geometrical and Statistical Alignment Approach for Low-Resolution Face Recognition
1 Introduction
2 Related Work
3 Framework for Visual Domain Adaptation
3.1 Problem Description
3.2 Model Formulation
3.3 New Objective Function
4 Experiments
4.1 Benchmark Datasets
4.2 Experimental Results
4.3 Experimental Analysis
4.4 Parameter Sensitivity Test
5 Conclusion
References
A Part Fusion Model for Action Recognition in Still Images
1 Introduction
2 Method
2.1 The Guided Attention Module
2.2 Two-Level Classification Networks
3 Experiments
3.1 Experimental Setup
3.2 Comparison with State-of-the-Art Method
3.3 Ablation Studies
4 Conclusion
References
An Empirical Study of Deep Neural Networks for Glioma Detection from MRI Sequences
1 Introduction
2 State of the Art
3 Materials and Methods
3.1 Material
3.2 Model Implementation
4 Results
4.1 Mixing All
4.2 Comparison with UNET3D
4.3 Deep Feature Extraction and Interpretation Analysis
5 Conclusion
References
Analysis of Texture Representation in Convolution Neural Network Using Wavelet Based Joint Statistics
1 Introduction
2 Methods and Materials
2.1 Model Description of VGG16
2.2 Overview of the PSS
2.3 Image Dataset
3 Experiments and Results
3.1 Experiment with LASSO Regression
3.2 Analysis of the Synthesized Image with VGG
3.3 Results
4 Conclusion and Discussion
References
Auto-Classifier: A Robust Defect Detector Based on an AutoML Head
1 Introduction
2 Related Work
3 Proposed Method
3.1 Convolutional Neural Architectures
3.2 Auto-Classifier
4 Experiments
4.1 DAGM2007
4.2 Results and Discussion
5 Conclusions
References
Automating Inspection of Moveable Lane Barrier for Auckland Harbour Bridge Traffic Safety
1 Introduction
2 Background
2.1 Deep Learning and Object Detection
2.2 SqueezeNet Evaluation and Architecture
3 Methodology
3.1 Design Decisions and Rationale of the Study
3.2 Extending Minority Class and Data Pre-processing
3.3 Dataset Distribution
4 Results
5 Discussion
6 Conclusion
References
Bionic Vision Descriptor for Image Retrieval
1 Introduction
2 Bionic Vision Descriptor
2.1 Motivation
2.2 Original Bionic Vision Descriptor
2.3 Extensional Bionic Vision Descriptor
2.4 Feature Selection and Extraction
3 Experimental Results
4 Conclusion
References
Brain Tumor Segmentation from Multi-spectral MR Image Data Using Random Forest Classifier
1 Introduction
2 Materials and Methods
2.1 Data
2.2 Pre-processing
2.3 Decision Making
2.4 Post-processing
2.5 Evaluation Criteria
3 Results and Discussion
4 Conclusions
References
CAU-net: A Novel Convolutional Neural Network for Coronary Artery Segmentation in Digital Substraction Angiography
1 Introduction
2 Related Work
3 Method
3.1 Feature Fusion Module
3.2 Pyramid Feature Concatenation
3.3 SE-Block
3.4 Loss Function
4 Dataset
5 Experiments
5.1 Implementation Details
5.2 Evaluation Metrics
5.3 Ablation Experiments
5.4 Comparing with Other Methods
6 Conclusion
References
Combining Filter Bank and KSH for Image Retrieval in Bone Scintigraphy
1 Introduction
2 Methodology
2.1 Texture Feature Extraction with Filter Bank
2.2 Supervised Retrieval with Kernels
3 Experiments
3.1 Dataset and Settings
3.2 Quantitative Comparison
3.3 Subjective Comparison
4 Conclusion
References
Contrastive Learning with Hallucinating Data for Long-Tailed Face Recognition
1 Introduction
2 Related Work
2.1 Face Recognition
2.2 Contrastive Learning
3 Method
3.1 Framework
3.2 Data Hallucinating
3.3 Contrastive Learning
3.4 Training and Inference
4 Experiments
4.1 Experiment Settings
4.2 Performance on Constrained Datasets
4.3 Performance on Unconstrained Datasets
4.4 Ablation Studies
4.5 Visualization Results
5 Conclusion
References
Deep Cascade Wavelet Network for Compressed Sensing-MRI
1 Introduction
2 Methods
2.1 Problem Formulation
2.2 Overall Structure
2.3 Deep Wavelet Block
2.4 CA Layer
2.5 DC Layer
3 Experiments
3.1 Dataset
3.2 Network Training and Evaluation
4 Results
4.1 Comparison of Different Methods
4.2 Ablation Study
5 Conclusion
References
Deep Patch-Based Human Segmentation
1 Introduction
2 Related Work
2.1 Surface Mapping
2.2 Deep Learning on Human Segmentation
3 Method
3.1 Overview
3.2 Surface Mapping
3.3 Neural Network and Implementation
4 Experimental Results
4.1 Dataset Configuration
4.2 Evaluation Metric
4.3 Visual and Quantitative Results
4.4 Ablation Study
5 Conclusion
References
Deep Residual Local Feature Learning for Speech Emotion Recognition
1 Introduction
2 Literature Reviews
3 The Proposed Model
3.1 Raw Data Preparation
3.2 Voice Activity Detection
3.3 Bias Frame Cleaning
3.4 Feature Extraction
3.5 Deep Learning
4 Experiments and Discussion
5 Conclusion
References
Densely Multi-path Network for Single Image Super-Resolution
1 Introduction
2 Related Work
3 Proposed Method
3.1 Network Framework
3.2 Densely Multi-path Block
3.3 Reconstruction Block
4 Experiments
4.1 Datasets and Metrics
4.2 Training Details
4.3 Comparisons with State-of-the-arts
5 Conclusions and Future Works
References
Denstity Level Aware Network for Crowd Counting
1 Introduction
2 Related Works
3 Proposed Method
3.1 Architecture
3.2 Density Level Estimator
3.3 Loss Function
4 Experiments
4.1 Datasets
4.2 Experimental Settings
4.3 Performance Comparison
4.4 Ablation Study
5 Conclusion
References
Difficulty Within Deep Learning Object-Recognition Due to Object Variance
1 Introduction
2 Related Work
3 Method
3.1 Datasets of Variances for Various NN Architectures
3.2 Distribution of Data with Sensitivity Analysis
4 Experiments
5 Conclusion
References
Drawing Dreams
1 Introduction
2 Related Work
3 Method
3.1 Information Extraction
3.2 Image Synthesis
3.3 Dream Generation
4 Experiment
4.1 Dataset
4.2 Quantitative Evaluation
4.3 Qualitative Comparison and User Studies
4.4 Results Display
5 Conclusion and Future Work
References
Encoder-Decoder Based CNN Structure for Microscopic Image Identification
1 Introduction
2 Neural Identification Technique
2.1 Image Processing
2.2 Convolutional Neural Network
2.3 CNN Encoder-Decoder Structure
3 Experiments
4 Conclusions
References
Face Manipulation Detection via Auxiliary Supervision
1 Introduction
2 Related Work
2.1 Face Manipulation Methods
2.2 Forgery Detection Methods
3 Methods
3.1 Texture Map Supervision
3.2 Blending Boundary Supervision
3.3 Loss Function
4 Experimental Results
4.1 Experimental Setting
4.2 Ablation Study
4.3 Evaluation on Faceforensic++
4.4 Generalizability Evaluation
5 Conclusion
References
Fine-Grained Scene-Graph-to-Image Model Based on SAGAN
1 Introduction
2 Related Work
3 Methodology
3.1 The Overall Architecture of Text-to-Image
3.2 Adding Self-attention in Object Layout
3.3 Improving the Stability of Cascaded Refinement Network
3.4 Discriminators and Loss
4 Experiments
4.1 Datasets
4.2 Evaluation
4.3 Experimental Results
5 Conclusions
References
Generative Adversarial Network Using Multi-modal Guidance for Ultrasound Images Inpainting
1 Introduction
2 Relate Work
3 Multi-modal Guided Generative Adversarial Network
3.1 Multi-modal Guided Network
3.2 Fine Inpainting Network
3.3 Training Detail
4 Experiment
4.1 Dataset and Metrics
4.2 Comparison with State-of-the-Arts Methods
4.3 Ablation Experiment
5 Conclusion
References
High-Level Task-Driven Single Image Deraining: Segmentation in Rainy Days
1 Introduction
2 Related Work
3 Method
3.1 Model Architecture
3.2 Training Method
4 A New Raindrop-Cityscapes Dataset
5 Experiments
5.1 Ablation Studies
5.2 Evaluation on Synthetic Dataset
5.3 Evaluation on the Real-World Dataset
6 Conclusion
References
Hybrid Training of Speaker and Sentence Models for One-Shot Lip Password
1 Introduction
2 Related Work
2.1 Neural Networks
2.2 Loss Function
3 Method
3.1 Data Preparation
3.2 Feature Extractor
3.3 Hybrid Model
4 Experiment and Results
4.1 Dataset
4.2 Experiment Settings
4.3 Performance Comparison of Single and Hybrid Model
4.4 Effect of Separable 3D Convolution
4.5 Speaker Model and Sentence Model in Hybrid Method
5 Summary
References
Identifying Real and Posed Smiles from Observers' Galvanic Skin Response and Blood Volume Pulse
1 Introduction
2 Background
2.1 Physiological Signals
3 Experimental Methodology
3.1 Smile Videos and Images Stimuli
3.2 Participants/Observers
3.3 Physiological Data Acquisition
3.4 Experimental Procedure
3.5 Signal Processing
3.6 Feature Extraction
4 Experimental Results and Discussion
4.1 Analysis of the Feature Performance
4.2 Feature Distributions
4.3 Predictive Data Testing
5 Conclusions
References
Image Generation with the Enhanced Latent Code and Sub-pixel Sampling
1 Introduction
2 Related Work
3 Methodology
3.1 Network Architecture
3.2 Modified Variational Lower Bound for Reliable Object Appearance
3.3 Sub-pixel Sampling for Eliminating Artifacts
4 Experiments and Analysis
4.1 Datasets and Evaluation Metrics
4.2 Comparing Analysis
4.3 Ablation Study
5 Conclusion
References
Joint Optic Disc and Optic Cup Segmentation Based on New Skip-Link Attention Guidance Network and Polar Transformation
1 Introduction
2 SLAG-CNN Network Structure
2.1 Skip-Link Attention Gate (SLAG)
3 Experiments and Analysis
3.1 Training Parameter Settings and Dataset
3.2 Evaluation Method
3.3 Analysis of Experimental Results
4 Ablation Study
4.1 Is the Attention Module Effective?
4.2 Does the Model Have Generalization?
5 Conclusion
References
LCNet: A Light-Weight Network for Object Counting
1 Introduction
2 Proposed Method
2.1 Architecture
2.2 Dilated Convolution
2.3 Ghost Module
3 Training Method
3.1 Ground Truth Generation
3.2 Evaluation Metrics
3.3 Training Details
4 Experiments
4.1 Accuracy Comparison
4.2 Speed Comparison
4.3 Analysis of Network Architecture
5 Conclusion
References
Low-Dose CT Image Blind Denoising with Graph Convolutional Networks
1 Introduction
2 Proposed Method
2.1 Noise Modeling for LDCT Image
2.2 Low-Dose CT Graph-Convolutional Network
3 Experiments
3.1 Datasets and Experimental Settings
3.2 Results on Synthetic LDCT Images
3.3 Ablation Study
3.4 Results on Real-World LDCT Images
4 Conclusion and Future Work
References
Multi Object Tracking for Similar Instances: A Hybrid Architecture
1 Introduction
2 Related Work
3 Methods
3.1 Annotation and Augmentation
3.2 Segmentation by Clustering
3.3 Error Detection
3.4 Architecture Overview
4 Implementation
5 Experiments and Results
5.1 Segmentation Quality
5.2 Robustness
6 Discussion
7 Conclusions
References
Multiple Sclerosis Lesion Filling Using a Non-lesion Attention Based Convolutional Network
1 Introduction
2 Related Work
3 Method
3.1 Non-Lesion Atttention Module
3.2 Network Design and Implementation
3.3 Loss Function
4 Results
4.1 Data
4.2 Qualitative Evaluation
4.3 Quantitative Evaluation
5 Conclusion
References
Multi-scale Object Detection in Optical Remote Sensing Images Using Atrous Feature Pyramid Network
1 Introduction
2 Related Work
2.1 CNN-Based Object Detection Algorithms
2.2 Multi-scale Feature Representations
2.3 Atrous Convolution
3 Method
3.1 Atrous Feature Fusing Module
3.2 Atrous Lateral Connection Block
4 Experiments
4.1 Results on NWPU VHR-10 Dataset
4.2 Ablation Study on NWPU VHR-10 Dataset
4.3 Results on RSOD
5 Conclusion
References
Object Tracking with Multi-sample Correlation Filters
1 Introduction
2 Related Work
3 CF Tracking
3.1 Ridge Regression and CF
3.2 Ridge Regression and KCF
4 Multi-sample KCF (MSKCF)
4.1 Objective Function
4.2 Weight of Filter Parameter
5 Experiments
5.1 Experimental Data and Evaluation Index
5.2 Compared Algorithms
5.3 Experimental Environment and Parameter Configuration
5.4 Experimental Results and Analysis
6 Conclusion
References
Real-Time Gesture Classification System Based on Dynamic Vision Sensor
1 Introduction
2 Background
2.1 Celex Camera Data
2.2 Event Data Reconstruction
3 Related Work
3.1 Gesture Recognition Based on Traditional Camera
3.2 Gesture Recognition Based on DVS Camera
4 Method Overview
4.1 Data Preprocessing
4.2 Proposed Network
4.3 ORB-Based Keyframe Detection
5 Dataset
6 Experiment
6.1 Implementation
6.2 Performance
6.3 Reconstruction and Keyframe Parameters Exploration
6.4 Ablation
7 Conclusion
References
Res2U-Net: Image Inpainting via Multi-scale Backbone and Channel Attention
1 Introduction
2 Related Work
3 Proposed Approach
3.1 Overview of the Proposed Network
3.2 Res2U-Net Architecture
3.3 Dilated Multi-scale Channel-Attention Block
4 Experiments
4.1 Quantitative Comparisons
4.2 Qualitative Comparisons
4.3 Ablation Study
5 Conclusion
References
Residual Spatial Attention Network for Retinal Vessel Segmentation
1 Introduction
2 Related Work
2.1 U-Net
2.2 ResNet
3 Method
3.1 Spatial Attention
3.2 Modified Residual Block
3.3 Residual Spatial Attention Block
4 Experiments
4.1 Datasets
4.2 Evaluation Metrics
4.3 Implementation Details
4.4 Results
5 Discussion and Conclusion
References
REXUP: I REason, I EXtract, I UPdate with Structured Compositional Reasoning for Visual Question Answering
1 Introduction
2 Related Work and Contribution
3 Methodology
3.1 Input Representation
3.2 REXUP Cell
4 Evaluation
4.1 Evaluation Setup
4.2 Performance Comparison
4.3 Ablation Study
4.4 Parameter Comparison
4.5 Interpretation
5 Conclusion
References
Simultaneous Inpainting and Colorization via Tensor Completion
1 Introduction
2 Related Work
3 Proposed Method
3.1 Preliminaries and Notations
3.2 Problem Formulation
3.3 ADMM Based Algorithm
4 Experiments
4.1 Inpainting
4.2 Colorization
4.3 Simultaneous Inpainting and Colorization
5 Conclusion
References
Take a NAP: Non-Autoregressive Prediction for Pedestrian Trajectories
1 Introduction
2 Proposed Method
2.1 Problem Definition and System Overview
2.2 Feature Encoders
2.3 Context Generators
2.4 Latent Variable Generator
2.5 Non-Autoregressive Decoder (NAD)
2.6 Implementation Details
3 Experiments
3.1 Datasets and Metrics
3.2 Comparison with Other Methods
3.3 Ablation Study
3.4 Different Prediction Lengths
3.5 Qualitative Results
4 Conclusion
References
Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People
1 Introduction
2 Related Work
3 Method
3.1 Temporal PoseNet
3.2 Pose Refinement
4 Experiments
4.1 Datasets
4.2 Metrics
4.3 Implementation Details
5 Results
5.1 Ablation Studies
5.2 Vertical Location and Depth
6 Conclusion
References
The Dynamic Signature Verification Using population-Based Vertical Partitioning
1 Introduction
1.1 Motivation
1.2 Novel Elements of the Proposed Approach
1.3 Structure of the Paper
2 Idea of the Signature Verification Using Vertical Partitioning
3 New Method for Signals Partitioning
3.1 Differential Evolution Algorithm and Structure of Individuals
3.2 Evaluation Function for the Dynamic Signature Signal Processing
4 Simulation Results
5 Conclusions
References
Triple Attention Network for Clothing Parsing
1 Introduction
2 Related Work
2.1 Clothing Parsing
2.2 Semantic Segmentation
2.3 Attention Model
3 Approach
3.1 Overall
3.2 Color Attention Module
3.3 Position/Channel Attention Module
4 Experiment
4.1 Dataset and Evaluation Metric
4.2 Implementation Details
4.3 Result on ModaNet Dataset
5 Conclusion and Future Work
References
U-Net Neural Network Optimization Method Based on Deconvolution Algorithm
1 Introduction
2 Materials and Methods
2.1 Database
2.2 Algorithm Design Mentality
2.3 Methods
3 Experimental Results
4 Segmentation Results
5 Conclusion
References
Unsupervised Tongue Segmentation Using Reference Labels
1 Introduction
2 Method
2.1 The Generation Part
2.2 The Discrimination Part
2.3 Loss Function
3 Experiments
3.1 Dataset and Pretraining
3.2 Implementation Details
3.3 Evaluation Methods and Experimental Result
3.4 Ablation Studies
4 Conclusion
References
Video-Interfaced Human Motion Capture Data Retrieval Based on the Normalized Motion Energy Image Representation
1 Introduction
2 Related Work
3 Overview
4 Algorithm
4.1 Normalized Motion Energy Image
4.2 Augmented Gabor Feature Extraction
4.3 Discriminative Vector Extraction
4.4 Similarity Metric by PLDA
5 Experiments
5.1 Platform and Implementation
5.2 Databases and Performance Metrics
5.3 Benchmark Algorithms
5.4 MAP Statistics
5.5 P@n Statistics and P-R Curves
5.6 Computing Efficiency
6 Conclusion and Future Work
References
WC2FEst-Net: Wavelet-Based Coarse-to-Fine Head Pose Estimation from a Single Image
1 Introduction
2 Related Work
3 Method
3.1 Overview of WC2FEst-Net
3.2 Wavelet Transform
3.3 Multi-stream Module
3.4 Fine-Grained Structure Feature Aggregation
3.5 Coarse-to-Fine Regression
4 Experiments
4.1 Datasets
4.2 Experiments and Analysis
4.3 Discussion
5 Conclusion
References
Natural Language Processing
A Memory-Based Sentence Split and Rephrase Model with Multi-task Training
1 Introduction
2 Preliminaries
3 Methodology
3.1 Memory-Based Transformer
3.2 Multi-task Training
3.3 Conditional VAE
4 Experiments
4.1 Dataset
4.2 Baseline
4.3 Setup
4.4 Results
5 Related Work
6 Conclusion
References
A Neural Framework for English-Hindi Cross-Lingual Natural Language Inference
1 Introduction
1.1 Motivation
1.2 Contribution
2 Related Work
3 Data Preparation
4 Model for Evaluation
4.1 Model
5 Experiments and Results
6 Error Analysis
7 Conclusion
References
A Token-Wise CNN-Based Method for Sentence Compression
1 Introduction
2 Related Work
2.1 Recurrent Neural Networks
2.2 Bidirectional Encoder Representations from Transformers
3 Method
3.1 Network Architectures
4 Experiments
4.1 Data
4.2 Experimental Setup
4.3 Experiments on Different Network Settings
4.4 Experiments w.r.t@?????. the Training Size
4.5 Quantitative Evaluations
4.6 Perception-Based Evaluations
5 Results
6 Discussion
7 Conclusions
References
Automatic Parameter Selection of Granual Self-organizing Map for Microblog Summarization
1 Introduction
2 Background Knowledge
3 Problem Formulation
4 Methodology
5 Experimental Setup
5.1 Datasets
5.2 Evaluation Measure
5.3 Parameter Settings
5.4 Comparative Methods
6 Discussion of Results
7 Conclusion
References
CARU: A Content-Adaptive Recurrent Unit for the Transition of Hidden State in NLP
1 Introduction
1.1 Related Work
2 Content-Adaptive Recurrent Unit
2.1 Data Flow of Hidden State and Weight
2.2 Transition of Hidden State
3 Experimental Results
3.1 Sentiment Analysis
3.2 Neural Machine Translation
4 Conclusion
References
Coarse-to-Fine Attention Network via Opinion Approximate Representation for Aspect-Level Sentiment Classification
1 Introduction
2 Related Work
3 Model
3.1 Contextual Module
3.2 Coarse-to-Fine Attention Module
3.3 Classification Module
4 Experiments
4.1 Datasets and Settings
4.2 Main Results and Discussions
4.3 Effects of Opinion Approximate Representation
4.4 Effects of Coarse-to-Fine Attention Algorithm
4.5 Case Study
5 Conclusion
References
Deep Cardiovascular Disease Prediction with Risk Factors Powered Bi-attention
1 Introduction
2 Methodology
2.1 Technical Details of RFPBiA Model
3 Results
3.1 Dataset and Evaluation Metrics
3.2 Models and Parameters
3.3 Experimental Results
4 Discussion
5 Conclusions
References
Detecting Online Fake Reviews via Hierarchical Neural Networks and Multivariate Features
1 Introduction
2 Related Work
2.1 Opinion Spam Detection
2.2 Neural Networks for Representation Learning
3 Methodology
3.1 Feature Extraction
3.2 Hierarchical Neural Networks for Classification
4 Experiments
4.1 Datasets and Evaluation Metrics
4.2 Feature Selection
5 Development Experiment
5.1 Results and Analysis
6 Conclusion
References
Error Heuristic Based Text-Only Error Correction Method for Automatic Speech Recognition
1 Introduction
2 Proposed Methodology
2.1 Problem Definition
2.2 Data Processing
2.3 Detector
2.4 Corrector
3 Experiment
3.1 Experiment Data
3.2 Metric
3.3 Model Setting
3.4 Result and Discussion
4 Conclusion
References
Exploration on the Generation of Chinese Palindrome Poetry
1 Introduction
2 Related Works
3 Methodology
3.1 Problem Definition
3.2 The First Line Generation
3.3 The Rest Lines Generation
4 Experiment
4.1 Datasets
4.2 Baselines
4.3 Metrics and Results
4.4 Human Evaluation
5 Conclusions
References
Improving Mongolian-Chinese Machine Translation with Automatic Post-editing
1 Introduction
2 Background and Related Work
3 Approach
3.1 Bilingual Alignment Representation
3.2 Prediction Module
3.3 CoRe Network
3.4 Joint Training
4 Experiment and Analysis
4.1 Datasets and Setting
4.2 Main Results and Analysis
4.3 Ablation Study
4.4 Case Study
5 Conclusion
References
Improving Personal Health Mention Detection on Twitter Using Permutation Based Word Representation Learning
1 Introduction
2 Related Work
3 Method
3.1 Language Model Pretraining
4 Experiments
4.1 Dataset
4.2 Data Preprocessing
4.3 Experimental Settings
5 Results and Discussion
6 Error Analysis
7 Conclusion
References
Learning Discrete Sentence Representations via Construction & Decomposition
1 Introduction
2 Related Work
3 Methodology
3.1 Preparation: Generating Anchor Vectors
3.2 Construction
3.3 Decomposition
3.4 Algorithmic Analysis
4 Experiments
4.1 Experimental Setup
4.2 Experimental Results and Analysis
4.3 Nearest Neighbor Retrieval
4.4 Ablation Study
5 Conclusion
References
Sparse Hierarchical Modeling of Deep Contextual Attention for Document-Level Neural Machine Translation
1 Introduction
2 Related Work
3 Our Model
3.1 Sentence-Level Encoder
3.2 Document-Level Encoder
3.3 Integration with Sentence-Level Encoder
3.4 Document-Level Decoder
3.5 Training Strategy of Model
4 Experiments
4.1 Dataset
4.2 Model Setup
5 Analysis and Discussion
5.1 Effect of Gate Portion
5.2 Overall Performance
5.3 Accuracy of Pronoun/Noun Translations
5.4 Examples of Translation
6 Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken