
Database Systems for Advanced Applications
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The three-volume set LNCS 13245, 13246 and 13247 constitutes the proceedings of the 26th International Conference on Database Systems for Advanced Applications, DASFAA 2022, held online, in April 2021.
The total of 72 full papers, along with 76 short papers, are presented in this three-volume set was carefully reviewed and selected from 543 submissions. Additionally, 13 industrial papers, 9 demo papers and 2 PhD consortium papers are included.
The conference was planned to take place in Hyderabad, India, but it was held virtually due to the COVID-19 pandemic.
More details
Other editions
Additional editions

Content
- Intro
- General Chairs' Preface
- Program Chairs' Preface
- Organization
- Contents - Part III
- Text and Image Processing
- Emotion-Aware Multimodal Pre-training for Image-Grounded Emotional Response Generation
- 1 Introduction
- 2 Related Work
- 3 Approaches
- 3.1 Overview
- 3.2 Pre-training
- 3.3 Fine-Tuning on the IgERG Task
- 3.4 Structure of Model Components
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Overall Results
- 4.3 Ablation Studies on Pre-training Tasks
- 4.4 Emotion Expression in Text Generation
- 4.5 Studies on the Dataset Selection
- 5 Conclusion
- References
- Information Networks Based Multi-semantic Data Embedding for Entity Resolution
- 1 Introduction
- 2 Problem Formalization
- 3 Multi-semantic Data Embedding Through Multitype Information Networks
- 3.1 Similarity Based Bipartite Network Embedding
- 3.2 Multi-semantic Embedding for Data with Attributes
- 4 Flexible Entity Resolution with Multi-semantic Data Embeddings
- 5 Experimental Evaluation
- 5.1 Experiments Setup
- 5.2 Comparisons with Existing Works
- 5.3 Detailed Analysis
- 6 Related Work
- 7 Conclusion
- References
- Semantic-Based Data Augmentation for Math Word Problems
- 1 Introduction
- 2 Related Work
- 2.1 Math Word Problem
- 2.2 Data Augmentation for Natural Language Processing (NLP)
- 3 Methodology
- 3.1 Problem Statement
- 3.2 Knowledge Augmentation
- 3.3 Logical Augmentation
- 4 Experiment
- 4.1 Dataset Analysis
- 4.2 Experimental Setup
- 4.3 Results
- 4.4 Case Study
- 5 Conclusion and Discussion
- References
- Empowering Transformer with Hybrid Matching Knowledge for Entity Matching
- 1 Introduction
- 2 Related Work
- 3 Entity Matching via GTA Framework
- 3.1 Preliminaries
- 3.2 Graph-Based Hybrid Embedding Module
- 3.3 Adaptive Transformer-Based Entity Matching
- 4 Experimental Evaluation
- 4.1 Experimental Settings
- 4.2 Main Results
- 4.3 Detailed Analysis
- 5 Conclusion and Outlook
- References
- Tracking the Evolution: Discovering and Visualizing the Evolution of Literature
- 1 Introduction
- 2 Related Works
- 3 Latent Relationship Learning
- 3.1 Context-Consistent Factor Graph
- 4 Literature Evolution Structure Discovery
- 4.1 Literature Evolution Discovery Problem
- 4.2 Approximate Algorithm
- 5 Experiments
- 5.1 Experiment Setting
- 5.2 Latent Relationship Study
- 5.3 Structure Study
- 5.4 Effectiveness of Our Solutions
- 5.5 Case Study
- 6 Conclusion
- References
- Incorporating Commonsense Knowledge into Story Ending Generation via Heterogeneous Graph Networks
- 1 Introduction
- 2 Related Work
- 3 Model
- 3.1 Overview
- 3.2 Heterogeneous Story Graph Construction
- 3.3 Story Heterogeneous Graph Network
- 3.4 Auxiliary Tasks
- 4 Experiments
- 4.1 Experiment Setup
- 4.2 Baseline Methods
- 4.3 Main Results
- 4.4 Ablation Study
- 4.5 Human Study and Case Study
- 5 Conclusion
- References
- Open-Domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
- 1 Introduction
- 2 Related Work
- 2.1 Dialogue Generation with External Knowledge
- 2.2 Virtual Knowledge Base
- 3 Model
- 3.1 Overview
- 3.2 Knowledge Branch
- 3.3 Generation
- 3.4 Training
- 4 Experiments
- 4.1 Dataset
- 4.2 Comparison Method
- 4.3 Implementation Details
- 4.4 Evaluation Metrics
- 5 Results and Discussion
- 5.1 Performance Evaluation
- 5.2 Ablation Study
- 5.3 Case Study
- 6 Conclusion
- References
- KdTNet: Medical Image Report Generation via Knowledge-Driven Transformer
- 1 Introduction
- 2 Related Work
- 2.1 Image Captioning
- 2.2 Report Generation
- 3 Models
- 3.1 Visual Grid Module
- 3.2 Graph Convolution Module
- 3.3 Auxiliary Language Module
- 3.4 KdTNet Encoder
- 3.5 KdTNet Decoder
- 3.6 Multimodal Information Fusion Module
- 3.7 Training
- 4 Experiment
- 4.1 Experimental Settings
- 4.2 Results on Report Generation
- 4.3 Ablation Studies
- 5 Conclusion
- References
- Fake Restaurant Review Detection Using Deep Neural Networks with Hybrid Feature Fusion Method
- 1 Introduction
- 2 Related Work
- 2.1 Traditional Machine Learning Approaches
- 2.2 Deep Learning Approaches
- 3 Methodology
- 3.1 Review Collection and Labeling
- 3.2 Review Feature Extraction
- 3.3 Fake Review Detection
- 4 Experiments and Results
- 4.1 Different Dataset Sizes
- 4.2 Ablation Study
- 4.3 Model Performance Comparison
- 5 Conclusion
- References
- Aligning Internal Regularity and External Influence of Multi-granularity for Temporal Knowledge Graph Embedding
- 1 Introduction
- 2 Related Work
- 2.1 Static Knowledge Graph Embedding
- 2.2 Temporal Knowledge Graph Embedding
- 3 Problem Formulation
- 4 Methodology
- 4.1 Element-Level Information Modeling
- 4.2 Fact-Level Information Modeling
- 4.3 Multi-granular Information Alignment
- 4.4 Model Learning
- 5 Experiments
- 5.1 Datasets
- 5.2 Evaluation Metrics and Baselines
- 5.3 Implementation Details
- 5.4 Results
- 5.5 Ablation Study
- 6 Conclusion
- References
- AdCSE: An Adversarial Method for Contrastive Learning of Sentence Embeddings
- 1 Introduction
- 2 Related Work
- 2.1 Sentence Embedding
- 2.2 Contrastive Learning
- 3 The Design of AdCSE
- 3.1 Problem Formulation
- 3.2 Backbone Network for Contrastive Learning
- 3.3 Adversaries for Hard Negatives Training
- 3.4 Learning Objective and Algorithm
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Main Results
- 4.3 Ablation Study
- 5 Further Analysis
- 5.1 Analysis of Embedding Space
- 5.2 Case Study on Semantic Similarity
- 5.3 Influence of Batch Size and Temperature
- 6 Conclusion
- References
- HRG: A Hybrid Retrieval and Generation Model in Multi-turn Dialogue
- 1 Introduction
- 2 Related Work
- 2.1 Single-Turn Response Matching
- 2.2 Multi-turn Response Matching
- 2.3 Single-Turn Response Generation
- 2.4 Multi-turn Response Generation
- 3 HRG Model
- 3.1 Current Turn and Context Attention
- 3.2 Retrieval
- 3.3 Hierarchical Fusion Encoder
- 3.4 Decoder
- 4 Experiment
- 4.1 Datasets
- 4.2 Baselines
- 4.3 Experiment Settings
- 4.4 Human Evaluation
- 4.5 Automatic Evaluation
- 5 Analysis
- 6 Conclusion and Future Work
- References
- FalCon: A Faithful Contrastive Framework for Response Generation in TableQA Systems
- 1 Introduction
- 2 Related Work
- 3 Task Definition and Preliminary
- 4 Proposed Approach
- 4.1 Imposters Construction
- 4.2 Contrastive Training
- 4.3 Contrastive Inference
- 4.4 Metrics
- 5 Experiments
- 5.1 Dataset
- 5.2 Baselines
- 5.3 Implementation Details
- 5.4 Evaluation Metrics
- 6 Result and Analysis
- 6.1 Performance on Automatic Metrics
- 6.2 Performance on Human Evaluation
- 6.3 Model Analysis
- 6.4 Case Study
- 7 Conclusion
- References
- Tipster: A Topic-Guided Language Model for Topic-Aware Text Segmentation
- 1 Introduction
- 2 Problem Formulation
- 3 Tipster for Topic-Aware Text Segmentation
- 3.1 Topic-Guided Sentence Encoder
- 3.2 Segment Boundary Predictor
- 3.3 Segment Topic Labeling
- 3.4 Joint Learning
- 4 Experiments
- 5 Conclusion
- References
- SimEmotion: A Simple Knowledgeable Prompt Tuning Method for Image Emotion Classification
- 1 Introduction
- 2 Related Work
- 3 SimEmotion
- 3.1 Knowledgeable Prompt Generation
- 3.2 Semantic Emotion Feature Extraction
- 3.3 Similarity Constrains Strategy
- 4 Experiments and Analysis
- 4.1 Classification Performance
- 4.2 Ablation Study
- 5 Conclusion
- References
- Predicting Rumor Veracity on Social Media with Graph Structured Multi-task Learning
- 1 Introduction
- 2 Related Work
- 3 Problem Statement
- 4 Methodology
- 5 Experiments
- 5.1 Datasets and Experiment Setup
- 5.2 Results of Rumor Verification with STL-GT and MTL-SMI
- 5.3 Ablation Tests
- 6 Conclusion
- References
- Knowing What I Don't Know: A Generation Assisted Rejection Framework in Knowledge Base Question Answering
- 1 Introduction
- 2 Task Definition
- 3 Methodology
- 3.1 Overview of GEAR
- 3.2 Generation Module
- 3.3 Re-ranking Module
- 4 Experiments
- 4.1 Datasets, Baselines and Training Details
- 4.2 Performance and Analysis
- 5 Conclusion
- References
- Medical Image Fusion Based on Pixel-Level Nonlocal Self-similarity Prior and Optimization
- 1 Introduction
- 1.1 Motivation and Contributions
- 2 Related Work
- 2.1 Nonlocal Self-similarity
- 2.2 Nonlocal Similar Pixels
- 3 Methodology
- 3.1 Detailed Information Estimation
- 3.2 Two-Stage Decomposition Framework
- 3.3 Image Fusion and Reconstruction
- 3.4 Fusion of Pseudo-Color Image
- 4 Experiments and Analysis
- 4.1 Experimental Setup
- 4.2 Experimental Results and Discussions
- 5 Conclusion
- References
- Knowledge-Enhanced Interactive Matching Network for Multi-turn Response Selection in Medical Dialogue Systems
- 1 Introduction
- 2 Related Work
- 2.1 Knowledge-Grounded Dialogue System
- 2.2 Medical Dialogue System
- 3 Knowledge Construction
- 3.1 External Knowledge Construction
- 3.2 Internal Knowledge Construction
- 4 Methodology
- 4.1 Problem Formalization
- 4.2 Representation Phase
- 4.3 Matching Phase
- 4.4 Aggregation Phase
- 5 Experiments
- 5.1 Dataset
- 5.2 Experimental Results
- 6 Conclusion
- References
- KAAS: A Keyword-Aware Attention Abstractive Summarization Model for Scientific Articles
- 1 Introduction
- 2 Related Works
- 3 COVID-SUM Dataset
- 4 Model Description
- 4.1 Keyword Encoder
- 4.2 Keyword-Aware Focused Attention Decoder
- 5 Experiments
- 5.1 Results
- 6 Conclusion
- References
- E-Commerce Knowledge Extraction via Multi-modal Machine Reading Comprehension
- 1 Introduction
- 2 Related Work
- 2.1 Machine Reading Comprehension
- 2.2 Multi-modal Information Extraction
- 3 Framework
- 3.1 Description-Question Pair Preparation
- 3.2 Multi-modal Encoder
- 3.3 Data Filter
- 3.4 Attribute Extraction by Machine Reading Comprehension
- 4 Experiments
- 4.1 Dataset
- 4.2 Baselines
- 4.3 Results and Analysis
- 5 Conclusion
- References
- PERM: Pre-training Question Embeddings via Relation Map for Improving Knowledge Tracing
- 1 Introduction
- 2 Problem Formulation
- 3 Method
- 3.1 Relation Map Exploitation
- 3.2 Embedding Aggregation
- 3.3 Difficulty Prediction
- 4 Experiments
- 4.1 Datasets
- 4.2 Experimental Setup
- 4.3 Performance Comparison
- 4.4 Ablation Study
- 5 Conclusion
- References
- A Three-Stage Curriculum Learning Framework with Hierarchical Label Smoothing for Fine-Grained Entity Typing
- 1 Introduction
- 2 Overview
- 2.1 Problem Definition
- 2.2 Framework
- 3 Method
- 3.1 Hierarchical Label Smoothing
- 3.2 Curriculum Learning
- 3.3 Training Process
- 4 Experiment
- 4.1 Datasets and Metrics
- 4.2 Baselines
- 4.3 Performance Comparison
- 4.4 Ablation Study
- 5 Conclusion
- References
- PromptMNER: Prompt-Based Entity-Related Visual Clue Extraction and Integration for Multimodal Named Entity Recognition
- 1 Introduction
- 2 Methodology
- 2.1 Task Definition
- 2.2 Overview
- 2.3 Prompt-Based Visual Clue Extractor
- 2.4 Multimodal Information Integration
- 2.5 Prediction
- 3 Experiment
- 3.1 Experimental Setups
- 3.2 Experimental Results
- 4 Conclusion
- References
- TaskSum: Task-Driven Extractive Text Summarization for Long News Documents Based on Reinforcement Learning
- 1 Introduction
- 2 Related Work
- 3 Model Architecture
- 3.1 Hierarchical Sentence Encoder
- 3.2 Pointer Network Sentence Decoder
- 4 RL with Our Reward Scheme
- 5 Experiment Results
- 5.1 Experiment Setup
- 5.2 Main Results
- 5.3 Ablation Study
- 6 Conclusion
- References
- Concurrent Transformer for Spatial-Temporal Graph Modeling
- 1 Introduction
- 2 Problem Definition
- 3 Methodology
- 3.1 Concurrent Spatial-Temporal Graph
- 3.2 Concurrent Spatial-Temporal Attention Module
- 3.3 Iterative Strategy
- 3.4 Overall Framework
- 4 Experiments
- 4.1 Datasets
- 4.2 Experimental Introduction
- 4.3 Performance Comparison
- 5 Conclusion
- References
- Towards Personalized Review Generation with Gated Multi-source Fusion Network
- 1 Introduction
- 2 Proposed Method
- 2.1 Problem Formulation
- 2.2 History-Aware Personalized Encoder
- 2.3 Review Generation with Gated Multi-source Decoder
- 3 Experiments
- 3.1 Experimental Setting
- 3.2 Performance Evaluation
- 3.3 Ablation Study
- 3.4 Case Study
- 4 Conclusion
- References
- Definition-Augmented Jointly Training Framework for Intention Phrase Mining
- 1 Introduction
- 2 Solution
- 2.1 Jointly-Training Framework
- 2.2 Definition-Augmented Representation
- 3 Experiments
- 4 Conclusion
- References
- Modeling Uncertainty in Neural Relation Extraction
- 1 Introduction
- 2 Proposed Methods
- 2.1 Distribution Encoder
- 2.2 Sampling Process
- 2.3 Variance Voting
- 2.4 Result Aggregator
- 2.5 Loss Functions
- 3 Experiments and Analysis
- 3.1 Dataset
- 3.2 Baselines
- 3.3 Evaluation on One-Instance Bags
- 3.4 Effectiveness of Variance Voting
- 3.5 Effectiveness of Sampling Process
- 4 Related Work
- 5 Conclusion
- References
- Industry Papers
- A Joint Framework for Explainable Recommendation with Knowledge Reasoning and Graph Representation
- 1 Introduction
- 2 Preliminaries
- 2.1 Problem Definition
- 2.2 Markov Decision Process for Knowledge Reasoning
- 3 The Proposed Model
- 3.1 Attentive Reinforcement Knowledge Graph Reasoning
- 3.2 Graph Representation Learning with Reasoned Paths
- 3.3 Joint Learning
- 4 Experiments
- 4.1 Experimental Settings
- 4.2 Experimental Results
- 5 Conclusions
- References
- XDM: Improving Sequential Deep Matching with Unclicked User Behaviors for Recommender System
- 1 Introduction
- 2 Our Approach
- 2.1 Problem Formulation
- 2.2 Base Sequential Recommendation
- 2.3 Sequential Recommendation with Unclicked User Behaviors
- 3 Experimental Setup
- 3.1 Datasets
- 3.2 Compared Methods
- 3.3 Implementation Details
- 4 Experiment Analysis
- 4.1 Overall Performances
- 4.2 Ablation Analysis
- 4.3 The Effect of Margin
- 4.4 Online A/B Test
- 5 Conclusion
- References
- Mitigating Popularity Bias in Recommendation via Counterfactual Inference
- 1 Introduction
- 2 Related Work
- 3 Preliminaries
- 4 Methodology
- 4.1 Causal View in Recommendation
- 4.2 Mitigating Popularity Bias
- 4.3 Debiased Recommendation Model
- 5 Experiments
- 5.1 Experimental Settings
- 5.2 Performance Comparison (RQ1)
- 5.3 Case Study (RQ2)
- 5.4 Case Study (RQ3)
- 6 Conclusion
- References
- Efficient Dual-Process Cognitive Recommender Balancing Accuracy and Diversity
- 1 Introduction
- 2 The Proposed Method
- 2.1 Framework
- 2.2 Preliminary
- 2.3 System 1: Intuitive Representation Module
- 2.4 System 2: Inference Module
- 2.5 CogRecDiv
- 3 Experiments
- 3.1 Sequential Settings
- 3.2 Main Results
- 3.3 Ablation Study
- 3.4 Case Study
- 4 Related Works
- 5 Conclusions
- References
- Learning and Fusing Multiple User Interest Representations for Sequential Recommendation
- 1 Introduction
- 2 Related Work
- 2.1 Sequential Recommendation
- 2.2 User Representation
- 2.3 Representations Fusion
- 3 Proposed Method
- 3.1 Problem Formulation
- 3.2 Embedding
- 3.3 Local-Level Representation Learning
- 3.4 Global-Level Representation Learning
- 3.5 Representation Gating
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Experimental Results
- 5 Conclusion
- References
- Query-Document Topic Mismatch Detection
- 1 Introduction
- 2 Topic Mismatch Detection (TMD) Approach
- 2.1 TMD Problem Definition
- 2.2 BiLSTM Baseline
- 2.3 BERT
- 2.4 BERT with Smoothed Input (SI)
- 2.5 BERT with Key-Phrases (KP) and Topic Distribution
- 3 Experiments
- 3.1 Dataset
- 3.2 Traditional Baseline Methods
- 3.3 Results Using Deep Learning Methods
- 3.4 Case Studies
- 4 Related Work
- 4.1 Topic Analysis for Queries
- 4.2 Document Representation
- 5 Conclusion
- References
- Beyond QA: `Heuristic QA' Strategies in JIMI
- 1 Introduction
- 2 Heuristic QA
- 2.1 Before User Querying: Intent Prediction
- 2.2 During User Querying: Query Auto-completion
- 2.3 After User Querying: Next Query Prediction
- 3 Application Effects and Automatic Model Retraining
- References
- SQLG+: Efficient k-hop Query Processing on RDBMS
- 1 Introduction
- 2 Background
- 2.1 Problem Definition
- 2.2 Related Work
- 3 Approach
- 3.1 Frontier Classification
- 3.2 Deduplicate by AdaptiveSet
- 3.3 Dynamic BFS/DFS Switch
- 4 Experiment
- 4.1 Datasets and Queries
- 4.2 Evaluation of Frontier Classification
- 4.3 Evaluation of AdaptiveSet
- 4.4 Evaluation of Dynamic BFS/DFS Switch
- 4.5 Overall Performance
- 4.6 Comparison with Graph Databases
- 5 Conclusion
- References
- Modeling Long-Range Travelling Times with Big Railway Data
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 4 Features for Remaining Journey Time Prediction
- 5 Baselines
- 5.1 Basic Methods
- 5.2 Machine Learning Methods
- 6 Attention Based LSTM (a-LSTM)
- 6.1 Attention Mechanism
- 7 Evaluation
- 7.1 Experimental Settings
- 7.2 Results
- 8 Conclusions
- References
- Multi-scale Time Based Stock Appreciation Ranking Prediction via Price Co-movement Discrimination
- 1 Introduction
- 2 The Proposed Framework
- 2.1 Multi-scale Time Based Encoder
- 2.2 Price Co-movement Discrimination Task
- 2.3 Stock Appreciation Ranking Prediction
- 3 Experiments
- 3.1 Performance Comparison with Baselines
- 3.2 Performance in Different Stock Holding Period
- 3.3 Ablation Analysis
- 4 Real-World Deployment
- 5 Related Work
- 6 Conclusions
- References
- RShield: A Refined Shield for Complex Multi-step Attack Detection Based on Temporal Graph Network
- 1 Introduction
- 2 Related Work
- 3 RShield Design and Implementation
- 3.1 Overview
- 3.2 Continuous-Time Dynamic Graph Construction
- 3.3 Node Embedding Based on TGN
- 3.4 Anomaly Edge Detection
- 4 Experiment and Evaluation
- 4.1 Experiment Setup
- 4.2 Experiment Results
- 4.3 Discussion
- 5 Conclusion
- References
- Inter-and-Intra Domain Attention Relational Inference for Rack Temperature Prediction in Data Center
- 1 Introduction
- 2 Preliminaries
- 3 I2A-RI Model
- 3.1 Multi-graph Relational Reasoning Encoder
- 3.2 Spatial-Temporal Prediction Decoder
- 4 Experiments
- 4.1 RATEDC
- 4.2 Experiment Setup
- 4.3 Performance Comparison
- 4.4 Ablation Study
- 4.5 Visualization
- 5 Conclusions
- References
- DEMO Papers
- An Interactive Data Imputation System
- 1 Introduction
- 2 VGAIN Imputation Algorithm
- 3 System Overview
- 4 Demonstrations
- References
- FoodChain: A Food Delivery Platform Based on Blockchain for Keeping Data Privacy
- 1 Introduction
- 2 The FoodChain Scenario and Features
- 3 The FoodChain System
- References
- A Scalable Lightweight RDF Knowledge Retrieval System
- 1 Introduction
- 2 System Architecture and Key Techniques
- 3 Evaluation and Demonstration
- References
- CO-AutoML: An Optimizable Automated Machine Learning System
- 1 Introduction
- 2 System Overview
- 3 Optimization Strategy for AutoML Techniques
- 4 Demonstration Scenarios and Conclusion
- References
- OIIKM: A System for Discovering Implied Knowledge from Spatial Datasets Using Ontology
- 1 Introduction
- 2 System Overview
- 3 Demonstration Scenarios
- 4 Conclusion
- References
- IDMBS: An Interactive System to Find Interesting Co-location Patterns Using SVM
- 1 Introduction
- 2 System Overview
- 3 Demonstration Scenarios
- 4 Conclusion
- References
- SeTS3: A Secure Trajectory Similarity Search System
- 1 Introduction
- 2 System Architecture
- 2.1 System Model
- 2.2 System Design
- 3 System Implementation
- 4 Demonstration
- 5 Conclusion
- References
- Data-Based Insights for the Masses: Scaling Natural Language Querying to Middleware Data
- 1 Introduction
- 2 Methodology
- 2.1 Data
- 2.2 System Overview
- 2.3 Rule Mapping
- 3 System Demonstration
- 4 Conclusion
- References
- Identifying Relevant Sentences for Travel Blogs from Wikipedia Articles
- 1 Introduction
- 2 Related Work
- 3 Our WikiBlogs Dataset
- 4 Blog Worthiness Score Prediction
- 5 Conclusion
- References
- PhD Constorium
- Neuro-Symbolic XAI: Application to Drug Repurposing for Rare Diseases
- 1 Research Problem
- 2 Current Development and Related Work
- 3 Methodology
- 3.1 Validation and Exploitation of Results
- 4 Current Results and Future Work
- References
- Leveraging Non-negative Matrix Factorization for Document Summarization
- 1 Problem and Motivation
- 2 Related Work
- 3 Summarization Methods
- 4 Data-Sets and Evaluation
- 5 Conclusion and Future Directions
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.