دانلود کتاب Information Management and Big Data: 4th Annual International Symposium, SIMBig 2017, Lima, Peru, September 4-6, 2017, Revised Selected Papers (Communications in Computer and Information Science, 795)

فهرست مطالب :

Preface
Reference
Organization
Contents
Parallelization of Conjunctive Query Answering over Ontologies
1 Introduction
2 The Enhanced Most Specific Concept (MSC) Method
2.1 Basic MSC Method
2.2 MSC Computation with Assertion Cycles
2.3 Syntactic Conditions
2.4 Parallelization of the MSC Method
3 Conjunctive Query Answering and SPARQL
4 Experimental Evaluation
4.1 MSC Method Accuracy
4.2 Parallelization
4.3 SPARQL Query Accuracy
5 Discussion and Future Work
6 Conclusion
References
Could Machine Learning Improve the Prediction of Child Labor in Peru?
1 Introduction
2 Theoretical Background
2.1 Logit Model
2.2 Artificial Neural Networks
2.3 Child Labor in Peru
3 Research Method
3.1 Measurement Model
3.2 Data Collection and Analysis
4 Results
4.1 Logit Results
4.2 Neural Network Results
4.3 Technique Comparison
5 Discussion
References
Impact of Entity Graphs on Extracting Semantic Relations
1 Introduction
2 Related Works
3 Community Graph of Entities
3.1 Definition of the Graph
3.2 Construction of the Community Graph
4 Relation Validation
4.1 Graph-Based Features
4.2 Linguistic Features
5 Data
5.1 Data for Computing Features
5.2 Data for Training and Testing the Models
6 Results and Discussion
6.1 Results on the Relation Validation Task
6.2 Results of Knowledge Base Population Task
7 Conclusion
References
Predicting Invariant Nodes in Large Scale Semantic Knowledge Graphs
1 Introduction
2 Related Work
3 Data
4 Methods
5 Results
5.1 Type Analysis
6 Application to Natural Language Generation
7 Conclusions
References
Privacy-Aware Data Gathering for Urban Analytics
1 Introduction
2 Related Works
3 Data Gathering Framework
4 Datasets
5 Dataset Statistics
6 Sentiment Analysis of Crimes in Peru
7 Conclusion
References
Purely Synthetic and Domain Independent Consistency-Guaranteed Populations in SHIQ(D)
1 Introduction
2 Synthetic Data Generation
2.1 Concept Assertions
2.2 Role Assertions
2.3 Data Assertions
3 Performances of JPOT
3.1 Domain TBox
3.2 Domain Rbox
3.3 Generated Aboxes
4 Related Works
5 Conclusion
References
Language Identification with Scarce Data: A Case Study from Peru
1 Introduction
2 Peruvian Indigenous Languages
3 Related Work
4 Corpus Development
5 Language Identification Model
5.1 Standard Supervised Learning
5.2 Deep Supervised Learning
6 Statistical Comparison Test
7 Results and Discussions
8 Conclusions and Future Work
References
A Multi-modal Data-Set for Systematic Analyses of Linguistic Ambiguities in Situated Contexts
1 Disambiguation and Structural Prediction
2 Linguistic Ambiguities in Situated Contexts
2.1 LASC Data-Set:V1
3 Multi-modal Parsing
3.1 A Proof-of-Concept Study
4 Discussion
References
Community Detection in Bipartite Network: A Modified Coarsening Approach
1 Introduction
2 Fundamentals
2.1 Basic Definitions
2.2 Multilevel Optimization
3 Community Detection Based on Multilevel Approach by Using One-Mode Projection
4 Experimental Results and Analysis
5 Conclusions
References
Reconstructing Pedestrian Trajectories from Partial Observations in the Urban Context
1 Introduction
2 Background Concepts and Related Work
2.1 Trajectory Segmentation
2.2 Map Matching
2.3 Inference
3 Reconstructing Uncertain Pedestrian Trajectories
3.1 Trajectory Segmentation
3.2 Map Matching
3.3 Inference
4 Experiments
4.1 Data Sets
4.2 Experimental Results
5 Conclusion
References
Author Index