Natural Language Processing and Information Systems

Name: Natural Language Processing and Information Systems | 17th International Conference on Applications of Natural Language to Information Systems, NLDB 2012, Groningen, The Netherlands, June 26-28, 2012. Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

17th International Conference on Applications of Natural Language to Information Systems, NLDB 2012, Groningen, The Netherlands, June 26-28, 2012. Proceedings

Gosse Bouma Ashwin Ittoo Elisabeth Métais Hans Wortmann(Herausgeber*in)

Springer (Verlag)

1. Auflage

Erschienen am 22. Juni 2012

400 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-31178-9 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Title Page
Preface
Organization
Table of Contents
Invited Talk
Syntax, Semantics and Pragmatics of Conceptual Modelling
Introductory Notions for Conceptual Modelling
Goals, Purposes and Deployment Functions of Conceptual Models
Abstraction and Conceptual Modelling
The Notion of the Model
Stachowiak, Aristoteles, Galilei and Mahr Properties of Models
Criteria for Appropriateness of an Artifact to Become a Model
The Hidden Background of Models
Language-Backed Modelling
Language Selection Matters
The Cognitive Insufficiency of the Entity-Relationship Modelling Language
Syntax of Conceptual Models: Structuring and `Functioning'
Morphology of Conceptual Models and the Form of Elements
The Lexicography and the Namespace of Models
Semantics of Conceptual Models
Kinds of Semantics
The Lexicology and the Namespace of Models
Pragmatics of Conceptual Models
General Pragmatics of Modelling in a Community of Practice
Visualisation or the `Phonetics' of Conceptual Models
Summary
References
Full Papers
Multi-dimensional Analysis of Political Documents
Motivation
Multi-dimensional Analysis
Data Preparation
Topic Creation
Experiments
Setting
Data Sources
Experimental Design
Results
Conclusions
References
Fake Reviews: The Malicious Perspective
Introduction
Writing Fake Reviews
Authenticity
Impact
Attack Strategies
Experiments
Authenticity
Corpus Sensitivity
Comparing Attack Strategies
Related Work
Conclusion
References
Polarity Preference of Verbs: What Could Verbs Reveal about the Polarity of Their Objects?
Introduction
Resources
Verb's Preference Determination
Hypothesis Testing
Classification of Prior Noun Polarities
Evaluation
Experiments Based on a Polarity Lexicon
The Case of Unseen Nouns
Related Work
Conclusion and Future Work
References
Labeling Queries for a People Search Engine
Introduction
Related Work
Query Labeling
KBP - Labeling Using Knowledge Base Probabilities
TPP - Labeling by Training-set Pattern Probabilities
KBC-TPP - Labeling by Knowledge Base Candidates Combined with Training-set Pattern Probabilities
KBP-TPP - Labeling by Knowledge Base Probabilities Combined with Training-set Pattern Probabilities
CRFs - Conditional Random Fields
Experiments
Knowledge Base
Data Sets
CRF Setup
Results
Conclusions and Future Work
References
Litmus: Generation of Test Cases from Functional Requirements in Natural Language
Introduction
Litmus
Entity Extractor
Identifying Testable Sentences
Breaking a Compound/Complex Sentence into Simple Sentences
Generating the Test Intents of a Simple Sentence
Creating Positive Test Case(s)
Creating Negative Test Case(s)
Experimental Validation and Discussion
Related Work
Conclusion
References
Extracting Multi-document Summarieswith a Double Clustering Approach
Introduction
Related Work
The SIMBA System
Identification
Matching
Filtering
Reduction
Presentation
Evaluation
Corpus
Results
Concluding Remarks
References
Developing Multilingual Text Mining Workflows in UIMA and U-Compare
Introduction
Related Work
Platforms Supporting Multilinguality
Multilingual Term Extraction
Methodology
Processing Multilingual Documents in UIMA/U-Compare
Enhancing Interoperability
Application Workflow: Multilingual Biomedical Term Extraction
Overview of the Application Workflow
Parallel Corpus
Data Pre-processing
Multilingual Term Extraction Using String Similarity
Evaluation of the Methodology
Evaluation of the Multilingual Workflow Application
Conclusions and Future Work
References
Geographic Expansion of Queries to Improve the Geographic Information Retrieval Task
Introduction
Related Work
GIR System Overview
GeoCLEF: The Evaluation Framework
Experiments and Results
Conclusions and Further Work
References
Learning Good Decompositions of Complex Questions
Introduction
Related Work
Overview of Our Approach
Training Data Generation
Filtering Important Sentences
Simplifying the Sentences
Sentence-to-Question Generation
Supervised Model
Feature Space
Learning and Testing
Evaluation and Analysis
Corpus
Cross-Validation
Intrinsic Evaluation
Extrinsic Evaluation
Feature Engineering
Conclusion and Future Works
References
A Semi Supervised Learning Model for Mapping Sentences to Logical form with Ambiguous Supervision
Introduction
Semantic Parsing for Ambiguous Supervision
Semantic Parsing for Unambiguous Supervision Using SVMs
Semantic Parsing with Ambiguous Supervision
Semantic Parsing with Ambiguous Supervision Using MEM
Semi-supervised Semantic Parsing with Ambiguous Supervision
The Brown Algorithm
Word-Cluster Based Features for MEM
Word Cluster for SVM
Experimental Results
Error Analysis
Conclusions
References
On the Effect of Stopword Removal for SMS-Based FAQ Retrieval
Introduction
Task Description and Data
Related Work
Experimental Setup
SMS Normalization and Correction
Retrieving Answers from FAQs
Filtering Out-of-Domain Queries
Retrieval Experiments and Results
Experiments on Training Data
Out-of-Domain Query Detection
Experiments on Test Data
Analysis and Discussion
Conclusions and Future Work
References
Wikimantic: Disambiguation for Short Queries
Introduction
Related Work
Method Overview
Concept Selection
Generative Model
Content-Based Topic Modeling:
ReferenceRank: $M_ R$
Disambiguation
Product Method
Mixture Method
Evaluation
Conclusion
References
Short Papers
Polish Language Processing Chains for Multilingual Information Systems
Introduction
Language Processing Chains
Polish Language Tools
Segmentation and Morphosyntactic Tagging
Noun Phrase Extraction and Multi-word Expression Lemmatisation
Named Entity Recognition
Current Work
Text Summarization and Coreference Resolution
Categorization and Machine Translation
Polish Linguistic Chain-Based NLP Demo Applications
i-Librarian and EUDocLib
PLDocLib
Conclusions
References
GPU-Accelerated Non-negative Matrix Factorization for Text Mining
Introduction
Document Clustering
The Non-negative Matrix Factorization Algorithm
Implementation
Benchmark Results
Conclusion
References
Generating SQL Queries Using Natural Language Syntactic Dependencies and Metadata
Introduction
Motivations and Problem Definition
Building Clauses Sets
Generating Queries
Preliminary Experiment and Related Work
Conclusions and Future Work
References
Two-Stage Named-Entity Recognition Using Averaged Perceptrons
Introduction
Problem Description
Related Work
Architecture
Recognition Stage
Classification Stage
Evaluation
Conclusion
References
Using Natural Language Processing to Improve Document Categorization with Associative Networks
Introduction
Associative Network
Creation of an Associative Network
Training of an Associative Network
Improving the Activation Pattern
Design of the Experiment
Constructing the Test Sets
Setup of the Experiment
Methods to Construct the Set of Synsets
TF-IDF Baseline
Experimental Results
Conclusions and Future Work
References
MLICC: A Multi-Label and Incremental Centroid-Based Classification of Web Pages by Genre
Introduction
Genre Classification of Web Pages
Multi-label Classification Methods
MLICC Approach
Representing a Web Page
Building Genre Centroids
Incremental Classification of New Web Pages
Time and Space Complexity
Evaluation
Corpus
Experiments and Results
Comparison with Other Multi-label Classifiers
Summary and Future Work
References
Classifying Image Galleries into a Taxonomy Using Metadata and Wikipedia
Introduction
Related Work
Taxonomy
Methodology
Experiments
Results
Conclusions and Future Work
References
Supervised HDP Using Prior Knowledge
Introduction
Related Work
Methods
Experiment
Results
User Study Results
Conclusions
References
User-Driven Automatic Resource RetrievalBased on Natural Language Request
Introduction
Related Work
Model of System Entities
Semantic Description Model
User Model
ResourceModel
NLP Module Algorithms
Named Entity Recognition Algorithm
Service Interface Entities Enrichment with WSD Algorithm
Experimental Study
Conclusion and Future Work
References
Integrating Lexical-Semantic Knowledge to Build a Public Lexical Ontology for Portuguese
Introduction
The Construction of Onto.PT
A Public Lexical Ontology for Portuguese
Contents
Availability
Conclusion and Further Work
References
From Ontology to NL: Generation of Multilingual User-Oriented Environmental Reports
Introduction
Multi-layered Ontology as Starting Point for Generation
Ontology-Based Natural Language Report Generation
Evaluation
Conclusion
References
Web-Based Relation Extractionfor the Food Domain
Introduction
Data and Resources
TheDifferentRelations
Method
Surface Patterns (PATT)
Statistical Co-Occurrence (CO-OC)
Relation between Title and Body of a Webpage (TITLE)
Experiments
Conclusion
References
Blog Distillation via Sentiment-Sensitive Link Analysis
Introduction
Sentiment-Sensitive Link Analysis for Blog Ranking
Experiments
Conclusions
References
Performing Groupization in Data Warehouses: Which Discriminating Criterion to Select?
Introduction
$GID$ Approach for Analysts Group Identification in Data Warehouses
Experimental Study
Conclusion
References
The Study of Informality as a Framework for Evaluating the Normalisation of Web 2.0 Texts
Introduction
Related Work
Our Evaluation Framework for Text Normalisation
Informality Analysis
Text Normalisation Process
Analysis
TENOR Qualitative Evaluation
TENOR Quantitative Evaluation
Conclusions and Future Work
References
Modeling Math Word Problems with Augmented Semantic Networks
Introduction
Related Work
Formal Representation of a Problem
Representation
Model-to-Equations Transformation
Iterative Refinement
Discussion
References
Improving Document-Level Sentiment Classification Using Contextual Valence Shifters
Introduction
Related Work
Feature Set and Method Description
Contextual Valence Shifters Feature Set
Feature Extraction
Experimental Setup
Results and Analysis
Results of E1
Results of E2
Conclusion and Future Work
References
Comparing Different Methods for Opinion Mining in Newspaper Articles
Motivation
Related Work
Pre-evaluation
Determination of Polarity
Word Based Methods
Pattern Based Action Chains
Evaluation
Conclusion and Future Work
References
Extracting Social Events Based on Timeline and Sentiment Analysis in Twitter Corpus
Introduction
Extracting Events Based on Timeline and Sentiment Analysis
Event Term Extraction Based on Timeline Analysis
Event Term Extraction Based on Sentiment Features
Event Term Extraction Based on Timeline and Sentiment Feature
Experiments and Evaluation
Conclusions
References
Can Text Summaries Help Predict Ratings? A Case Study of Movie Reviews
Introduction
Related Work
Experimental Setup
Corpora
Experiments
Evauation and Discussion
Conclusion and Future Work
References
Towards User Modelling in the Combatag ainst Cyberbullying
Introduction
The Plag-Inn Algorithm
Experimental Results
Related Work
Conclusion
References
On the Application of Spell Correction to Improve Plagiarism Detection
Introduction
Methods
A Shallow Knowledge Based Plagiarism Detector
A Ranker Based Speller
Experimentation and Results
Conclusions and Future Work
References
PIRPO: An Algorithm to Deal with Polarity in Portuguese Online Reviews from the Accommodation Sector
Introduction
Related Work
Our Approach to Recognise Polarity in Portuguese Online Reviews
Experiment, Evaluation and Discussion on the Results
Final Remarks
References
Posters
Towards Interrogative Types in Task-Oriented Dialogue Systems
Introduction
Question Types
Task-Oriented Interrogative Types
Conclusion and Future Work
References
Teaching Business Systems to Agree
Introduction
The B2B Reference Model
Design of the Knowledge Base
Conclusion
References
Improving Chinese Event Construction Extraction with Lexical Relation Pairs
Introduction
Chinese Event Construction Extraction
Extraction with LRP Information
Experimental Results
Extraction System with Automatic LRPs
Conclusion
References
A Classifier Based Approach to Emotion Lexicon Construction
Introduction
Construction of Lexical Network
Fuzzy Clustering Cum SVM Based Classification
Experiments
Conclusion and Future Work
References
Technical Term Recognition with Semi-supervised Learning Using Hierarchical Bayesian Language Models
Introduction
HPYLM and VPYLM
Combining Language Models
Character-Level HPYLM
Introduction of Tokens
Distant-Sampling
Experiments
Supervised Technical Term Recognition
Technical Term Recognition by Using Semi-supervised Learning
Conclusion
References
An Experience Developing a Semantic Annotation System in a Media Group
Introduction
NASS Methodology
Experimental Evaluation
Related Work
Conclusions and Further Work
References
From Requirements to Code: Syntax-Based Requirements Analysis for Data-Driven Application Development
Introduction
Related Work
Syntax-Based Requirements Analysis for Data-Driven Applications
Entity Extraction
Attributes and Relationships Extraction
Experimental Results
Conclusions and Future Work
References
Structuring Political Documents for Importance Ranking
Introduction
Parliamentary Information Systems
Importance Ranking of Debates
Evaluation
Conclusions and Future Work
References
Author Disambiguation Using Wikipedia-Based Explicit Semantic Analysis
Introduction
Related Work
ESA-Based Author Disambiguation
Evaluation
Conclusion
References
Automatic Population of Korean Information in Linking Open Data
Introduction
Extending LOD with Korean Information
Conclusion and Future Work
References
Initial Results from a Study on Personal Semantics of Conceptual Modeling Languages
Introduction
Our Method for Eliciting Conceptual Understandings
Results of the First Observation Moment
General Discussion
Conclusion and Future Work
References
Lexical Knowledge Acquisition Using Spontaneous Descriptions in Texts
Introduction
The Word and Its Gloss
Definition
Gloss Extraction
Gloss Ranking
Experiments
Conclusion and Future Work
References
Interacting with Data Warehouse by Using a Natural Language Interface
Introduction
A NL Interface for OLAP Queries
Processing NL Queries
Extracting OLAP Query Elements
OLAP Query Generation
Conclusions and Future Work
References
Processing Semantic Keyword Queries for Scientific Literature
Introduction
A Representation Scheme for Analyzed Documents
Structured Semantic Keyword Queries
Conclusion
References
Arabic Rhetorical Relations Extraction for Answering "Why" and "How to" Questions
Introduction
Methodology for RST-Based Question Answering
Text Structure Derivation
Rhetorical Relations Selection
Determining the Elementary Units and Rhetorical Relations
Evaluation
Conclusion
References
Facets of a Discourse Analysis of Safety Requirements
The LELIE Project
Safety Requirements
Discourse Structures of Requirements
The Discourse Structure of Safety Requirements
Results and Performances
Perspectives
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken