Linking Theory and Practice of Digital Libraries

Name: Linking Theory and Practice of Digital Libraries | 28th International Conference on Theory and Practice of Digital Libraries, TPDL 2024, Ljubljana, Slovenia, September 24-27, 2024, Proceedings, Part I
Brand: Springer
Price: 149.79 EUR
Availability: OnlineOnly

28th International Conference on Theory and Practice of Digital Libraries, TPDL 2024, Ljubljana, Slovenia, September 24-27, 2024, Proceedings, Part I

Apostolos Antonacopoulos Annika Hinze Benjamin Piwowarski Mickaël Coustaty Giorgio Maria Di Nunzio Francesco Gelati Nicholas Vanderschantz(Editor)

Springer (Publisher)

Published on 25. September 2024

XXVI, 432 pages

E-Book

PDF with digital watermarking

System requirements

978-3-031-72437-4 (ISBN)

€149.79incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Keynotes
Libraries, Digital Libraries, and Data: 30 years of Development in Central Europe
Searching for Climate Impact
Impresso Beyond Borders: Connecting Historical Newspapers and Radio
Contents - Part I
Contents - Part II
Full Papers
Learning Reading Order via Document Layout with Layout2Pos
1 Introduction
2 Related Work
2.1 Multimodal Pre-trained Language Models
2.2 Addressing Reading Order Issues
2.3 Generative Methods for Information Extraction
3 Preliminary Experiments: OCR Serialization Errors
4 Reconstructing Positional Information from 2D Positions
4.1 Encoding Layout Information
4.2 Learning 1D Position Embeddings from Layout Information
4.3 Integrating Layout2Pos Into a Sequence-to-Sequence Framework
5 Experiments
5.1 Data
5.2 Experimental Settings
5.3 Visual Information Extraction
6 Results and Discussion
6.1 Next Token Position Prediction
6.2 Visual Information Extraction
7 Conclusion
8 Limitations
References
SWARM-SLR - Streamlined Workflow Automation for Machine-Actionable Systematic Literature Reviews
1 Introduction
2 Related Work
3 Approach
3.1 Requirements
3.2 Tools
3.3 Workflow
4 Evaluation
4.1 Design
4.2 Results
5 Discussion and Future Work
6 Conclusion
References
A Reputation System for Scientific Contributions Based on a Token Economy
1 Introduction
2 Problem Statement
3 Approach
3.1 Stakeholders
3.2 Use Case
3.3 Requirements and Constraints
3.4 Reputation Token Economy
4 Implementation
4.1 Reputation Token
4.2 User Interface and Visualization
5 Related Work
6 Qualitative Evaluation
7 Discussion
8 Conclusion
9 Future Work
References
Bibliotheca Eugeniana Digital-Unveiling and Visualizing the Treasures of Prince Eugene of Savoy's Library
1 Introduction
2 From a Handwritten Catalog to a Digital Edition
2.1 Digitizing the Handwritten Catalog
2.2 Supralibros Analyses
3 Visualizing the Bibliotheca Eugeniana
4 Discussion
References
Comparative Analysis of Evaluation Measures for Scientific Text Simplification
1 Introduction
2 Measures
3 Corpora
4 Results
4.1 Simplicity
4.2 Meaning Preservation
5 Discussion
5.1 Interpretation of Results
5.2 Limitations
6 Conclusion
References
Promoting Interoperability on the Datasets of the Arrowheads Findings of the Chalcolithic and the Early/Middle Bronze Age
1 Introduction
2 Background
3 Methodology
3.1 Objectives
3.2 Process
4 Results
4.1 The Arrowhead Metadata Application Profile Domain Model
4.2 The Arrowhead Metadata Application Profile (Ah MAP)
5 Discussion
6 Conclusion and Future Work
References
Tracing the Retraction Cascade: Identifying Non-retracted but Potentially Retractable Articles
1 Introduction
2 Literature Review
2.1 Importance of Citations
2.2 Citations of Retracted Articles
3 Dataset Formulation
3.1 Dataset Design Decision
4 Retraction-Centric Approach
5 Experimental Setting and Evaluation
6 A Case in Point
7 Discussion and Conclusion
8 Limitation and Future Work
References
Mapping Techniques for an Automated Library Classification: The Case Study of Library Loans at Bibliotheca Hertziana
1 Introduction
2 Related Work
3 Methodology Overview
3.1 Data Visualisation
3.2 Generation of Subjects and Descriptions
3.3 Limitations
4 Case Study Investigation
5 Evaluation Insights
5.1 Expert Feedback
6 Conclusion
References
LIT: Label-Informed Transformers on Token-Based Classification
1 Introduction
2 Related Work
3 Model
4 Experiment
4.1 Datasets
4.2 Baseline
4.3 Settings
5 Results and Discussion
5.1 Historical NER
5.2 Term Extraction
6 Conclusion
References
Improving Retrieval and Expression of Iconographical and Iconological Semantic Statements: An Extension of the ICON Ontology
1 Introduction
2 The ICON Ontology
3 Extension Motivation
3.1 Iconology Dataset
3.2 IICONGRAPH
3.3 Content Motivation
3.4 Technical Motivation
4 Extension Description
5 Evaluation
5.1 Datasets
5.2 Competency Questions Evaluation
5.3 Efficiency Evaluation
6 Conclusion
References
Scholarly Quality Measurements: A Systematic Literature Review
1 Introduction
2 Background and Related Work
3 Methodology
3.1 Research Questions
3.2 Search Strategy
3.3 Selection Criteria
3.4 Data Extraction
3.5 Conduct
3.6 Results and Discussion
4 Conclusion
References
Assessing the Accessibility and Usability of Web Archives for Blind Users
1 Introduction
2 Related Work
2.1 Web Accessibility
2.2 Web Usability for Blind Users
3 Materials and Methods
3.1 Accessibility Analysis of Web Archives
3.2 Usability Analysis of Web Archives
4 Results
4.1 Accessibility of Web Archives
4.2 Usability Analysis of Web Archives
4.3 Qualitative Feedback
5 Discussion
5.1 Unique Issues of Web Archives
5.2 Limitations and Future Work
5.3 Suggestions for Web Archive Developers
5.4 Suggestions for Assistive Technologies Developers
6 Conclusion
References
Leveraging Transfer Learning for Article Segmentation in Historical Newspapers
1 Introduction
2 Preliminaries
2.1 Transfer Learning
2.2 Pre-trained Models
2.3 Concepts and Definitions
3 Related Work
4 Methodology
4.1 Network Architecture
4.2 Models Description
4.3 Model Training
4.4 Post-processing and Article Segmentation Module
5 Experimental Setup and Results
5.1 Datasets and Evaluation Metrics
5.2 Results and Discussion
6 Conclusions and Future Outlook
References
Findings Papers
Multi-dimensional Edge-Embedded GCNs for Arabic Text Classification
1 Introduction
2 Related Work
3 Methodology
4 Experiments
4.1 Datasets
4.2 Baselines
4.3 Experimental Results
4.4 Impact of Edge Dimensions
4.5 Impact of Varying Pooling Method
4.6 Complexity Analysis
4.7 Qualitative Analysis
5 Conclusion and Future Work
References
LIAS: Layout Information-Based Article Separation in Historical Newspapers
1 Introduction
2 Related Work
3 The LIAS Model
3.1 Separator Lines Detection and Region Segmentation
3.2 Paragraphs Grouping and Linking
3.3 Link Classification
4 Experiments
4.1 Dataset
4.2 Metrics
4.3 Benchmarks
4.4 Detailed Setup and Hyperparameters
5 Results and Discussion
5.1 Ablation Study
6 Conclusion and Limitations
References
CALM: Context Augmentation with Large Language Model for Named Entity Recognition
1 Introduction
2 Backbone Model
3 Framework
3.1 What to Ask?
3.2 How Does a LLM React to Different Formulations?
4 Protocol
4.1 Datasets
4.2 Baselines and Effectiveness Metrics
4.3 Qualitative Metrics
4.4 Training Details
5 Results
5.1 Measuring the Effectiveness of LLM-Based Context Augmentation
5.2 Analyzing the Quality of Generated Contexts
6 Related Work
7 Conclusion
References
Database Approaches to the Modelling and Querying of Musical Scores: A Survey
1 Introduction
2 The Content of a Musical Score
3 Document-Oriented Models
3.1 ASCII-Based Documents
3.2 Semi-structured Documents
4 Graph-Oriented Models
5 Time-Series-Oriented Models
5.1 Time-Series Algebra
5.2 Representation in an Euclidean Space
6 Discussion
7 Conclusion and Perspectives
References
Content-Based Dataset Retrieval Methods: Reproducibility of the ACORDAR Test Collection
1 Introduction
2 Original Contribution
3 Analysis of the ACORDAR Test Collection
4 Reproducibility Results
5 Further Analyses on the Impact of Data
6 Conclusions
References
Enhancing Identification of Scholarly Reference on YouTube
1 Introduction
2 Related Work
2.1 Investigation of Medical and Health-Related Information on YouTube
2.2 YouTube Videos Cited from Scholarly Articles
2.3 Bibliometric/Quantitative Analysis of Scholarly References on YouTube
3 Materials and Methods
3.1 Methodological Approaches by Altmetric and the Proposed Method
3.2 Dataset Construction
3.3 Structure of the Dataset
3.4 Analysis Methods
4 Results and Discussion
4.1 Comparison between the dataset constructed by the proposed method and the Altmetric dataset
4.2 Characteristics of external links as scholarly reference on YouTube
4.3 Contribution of each domain name to dataset coverage
5 Conclusion
References
Mining Literary Trends: A Tool for Digital Library Analysis
1 Introduction
2 Related Work
2.1 Topic Modeling
2.2 Large Language Models
2.3 Data Visualization
2.4 Tools for Digital Libraries
2.5 Our Proposal
3 Software Architecture and Functionality
3.1 Metadata Ingestion and Aggregation
3.2 PDF Knowledge Extraction
3.3 Metadata Aggregation and Normalization
3.4 Interactive Visualization
4 Use Case
4.1 Data Set Overview
4.2 Methodology and Analysis
5 Conclusion
References
PRET19: Automatic Recognition and Indexing of Handwritten Loan Registers from 19th Century Parisian Universities
1 Introduction
2 Loan Registers for Parisian Libraries in the 19th Century : Description of the Corpus
3 Building a Relational Database for Nineteenth-Century Library Loan Registers
3.1 Principles of the Data Modeling
3.2 Description of the Data Model
4 Semi-automatic Indexing of Handwritten Registers
4.1 Analysis of the Corpus Complexity
4.2 Description of the Workflow
5 Conclusion and Future Work
6 Appendices
6.1 Data model detailled
6.2 Structure of the website
References
Leveraging Open Large Language Models for Historical Named Entity Recognition
1 Introduction
2 Related Work
2.1 Named Entity Recognition in Historical Corpora
2.2 Large-Scale Language Models
3 Few-Shot Prompting for Historical NER
3.1 Datasets
3.2 Instruct Models
3.3 Prompt Designs
3.4 Post-processing Steps
3.5 Evaluation Metrics
4 Results
5 Conclusion
References
Enriching Archival Linked Data Descriptions with Information from Wikidata and DBpedia
1 Introduction
2 Background
2.1 ArchOnto
2.2 DBpedia
2.3 Wikidata
3 Methodology
4 Results and Discussion
4.1 Identification of Entities and Properties
4.2 Manual Representation of ``Processo de João''
4.3 Properties to Extend the Model
5 Conclusions
References
OpenPSS: An Open Page Stream Segmentation Benchmark
1 Introduction
2 Related Work
2.1 Page Stream Segmentation
2.2 Other Datasets
3 Method
3.1 Datasets
3.2 PSS Variants
3.3 Models
3.4 Model Ensembling
3.5 Evaluation
4 Results
4.1 Standard Page Stream Segmentation Task
4.2 Robust Page Stream Segmentation Task
4.3 Model Ensembling
5 Relevance for Information Retrieval
6 Discussion and Future Work
7 Conclusion
References
Correction to: Comparative Analysis of Evaluation Measures for Scientific Text Simplification
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Linking Theory and Practice of Digital Libraries

Description

More details

Other editions

Additional editions

Content

System requirements