Multidisciplinary Information Retrieval

Name: Multidisciplinary Information Retrieval | 5th Information Retrieval Facility Conference, IRFC 2012, Vienna, Austria, July 2-3, 2012, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

5th Information Retrieval Facility Conference, IRFC 2012, Vienna, Austria, July 2-3, 2012, Proceedings

Michail Salampasis Birger Larsen(Herausgeber*in)

Springer (Verlag)

Erschienen am 21. Juni 2012

X, 153 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-31274-8 (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
Preface
Organization
Table of Contents
Patent Search
Learning-Based Pseudo-Relevance Feedback for Patent Retrieval
Introduction
Related Work
Establishing a Baseline
Estimating the Query Model
Estimating the Relevance Model
Finding Effective Feedback Documents
Experimental Methodology and Results
Experimental Setup
Usefulness of Effective Feedback Documents
Predicting the Effectiveness of a Feedback Document
Parameter Sensitivity
Conclusions
Learning-Based Pseudo-Relevance Feedback for Patent Retrieval
Introduction
Related Work
Structural and Topical Dimensions in Patent Text
Extraction of Parallel Text
Experimental Data
Textual Similarities across IPC Domains
Cross-Domain Translation
Compound Splitting on Textual Domains
Discussion
References
Query Enhancement for Patent Prior-Art-Search Based on Keyterm Dependency Relations and Semantic Tags
Introduction
Background and Related Work
Proposed Query Formulation Method
System Description
Term Annotation by Semantic Tags
Term Weighting by Keyterm Dependency Relations (KDR)
Query Formulation
Patent Indexing and Retrieval
Experiments and Results
Test Collection and Evaluation Measures
Experimental Results
Overall Summary
Conclusion
References
Web Search
Analysis and Detectionof Web Spam by Means of Web Content
Introduction
Related Work
Detection of Spam by Means of Content Analysis
Detection of Some Kinds of Web Spam
SAAD Heuristics for Web Spam Detection
Method for Web Spam Detection
Experimental Results
Dataset
Experimental Setup
Results in Web Spam Dataset of Webb
Results in Web Spam Dataset of Yahoo!
Conclusions
Future Work
References
Discovery of Environmental Nodes in the Web
Introduction
Related Work
Empirical Study of Environmental Websites
General Framework
Web Search
Basic Queries
Extended Queries
Site Post Processing
Classification
Textual Features Extraction
Experimental Study
Web Search Step
Classification Step
Final Results
Conclusions
References
Web Searching with Entity Mining at Query Time
Introduction
Background and Related Work
NEM at Query Time
On Exploiting Linked Open Data
Experimental Results
Comparative Evaluation of Entity Ranking Methods by Users
Contents Mining versus Snippet Mining
Linked Data-Related Experimental Results
Concluding Remarks
References
Applications
Patent and Norm Exploration with the m2n Knowledge Discovery Suite
Challenges in Patent and Norm Retrieval
m2n Knowledge Discoverer for Norm and Patent Exploration
Image Analysis
Accessing Data
Summary
References
Hierarchical Classification of Web Documents by Stratified Discriminant Analysis
Introduction
Related Research
Linear Discriminant Analysis
Stratified Discriminant Analysis
Experimental Analysis
Dataset
Models
Performance Measures
Results
Conclusions and Future Work
References
PatMedia: Augmenting Patent Search with Content-Based Image Retrieval
Introduction
PatMedia Search Engine
Results and Evaluation
Results and Quantitative Evaluation
Patent Search Scenarios and Qualitative Evaluation
Conclusions
References
Query Formulation and Analysis
Generating Variant Keyword Forms for a Morphologically Complex Language Leads to Successful Information Retrieval with Finnish
Introduction
Inflected Keyword Generation for Finnish
Generators
Evaluation
Basic Evaluation
Evaluation with Other Base Form Creation Method
Generated Runs in the Lemmatized Index
Searching with Variant Keyword Forms in the Web
Discussion and Conclusions
References
Analyzing Query Logs of USPTO Examiners to Identify Useful Query Terms in Patent Documents for Query Expansion in Patent Searching: A Preliminary Study
Introduction
Related Work
Query Log Analyses
Experiment Set Up
General Statistics
Acquiring Lexical Knowledge from Patent Documents
Experiment Set Up
SFT and Lexical Knowledge Detection
Conclusions and Future Work
References
Discovering Relevant Features for Effective Query Formulation
Introduction
Related Work
Query Formulation
Phrase Extraction
Basic Definitions
Frequent Patterns and Closed Patterns
Closed Sequential Patterns
The Pattern Deploying Method
Our Approach
Pattern Refinement
Mining Negative Relevance Feedback
Selecting Negative Documents
Feature Extraction
Evaluation and Discussion
Experimental Dataset
Data Preprocessing and Measures
Baseline Models and Settings
Minimum Support Thresholds
Comparison to Pattern-Based Methods
Comparison to Term-Based Methods
Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken