Digital Libraries for Open Knowledge 23rd International Conference on Theory and Practice of Digital Libraries, TPDL 2019, Oslo, Norway, September 9-12, 2019, Proceedings

• Main Authors: International Conference on Theory and Practice of Digital Libraries (TPDL), Doucet, Antoine
• Format: eBook Book
• Language: English
• Published: Cham Springer Nature 2019; Springer; Springer International Publishing AG
• Edition: 1
• Series: Lecture Notes in Computer Science (11799)
• Subjects: Data processing Computer science; Digital libraries > Congresses

This book constitutes the proceedings of the 23rd International Conference on Theory and Practice of Digital Libraries, TPDL 2019, held in Olslo, Norway, in September 2019. The 16 revised full papers,12 short papers and 18 poster papers presented were carefully reviewed and selected from 75 submissi...

Table of Contents:

• The OpenAIRE Research Community Dashboard: On Blending Scientific Workflows and Scientific Publishing -- 1 Introduction -- 2 Digital Laboratories and Scholarly Communication Ecosystem: The Gap -- 3 The OpenAIRE Infrastructure -- 4 The OpenAIRE Research Community Dashboard -- 5 Real-Case Scenarios -- 5.1 The European Marine Science RCD Gateway -- 5.2 The EPOS Research Infrastructure RCD Gateway -- 6 Related Work -- 7 Conclusions and Future Work -- References -- A Framework for Citing Nanopublications -- 1 Introduction -- 2 Background -- 3 Use Case: DisGeNET -- 4 The Nanocitation Framework -- 5 The Nanocitation System -- 6 Conclusion and Future Work -- References -- Analysis of Transaction Logs from National Museums Liverpool -- 1 Introduction -- 2 Related Work -- 2.1 Background of This Study -- 2.2 Cultural Heritage User Groups -- 2.3 Transaction Log Analysis -- 3 Methodology -- 3.1 Analysing the Logs -- 3.2 Clustering the Logs -- 4 Findings -- 4.1 Website Interactions -- 4.2 Museum and Gallery Access -- 4.3 Page-Level Access -- 4.4 Sessions -- 5 Discussion -- 5.1 Clustering Results -- 5.2 Describing the Clusters -- 6 Conclusions and Future Work -- Knowledge Graph Implementation of Archival Descriptions Through CIDOC-CRM -- 1 Introduction -- 2 Description Models for Cultural Heritage -- 3 The CIDOC-CRM Ontology in Archives -- 4 A Prototype CIDOC-CRM Knowledge Graph -- 4.1 Multiple Inheritance: the Diamond Problem -- 4.2 Validation Trade-Offs -- 5 Conclusions -- References -- Investigating Correlations of Inter-coder Agreement and Machine Annotation Performance for Historical Video Data -- 1 Introduction -- 2 Related Work -- 3 Inter-coder Agreement Study (Concepts and Persons) -- 3.1 Dataset of Historical Concepts and Personalities -- 3.2 Study Participants -- 3.3 Experimental Design -- 3.4 Results -- 4 Predicting Concept Classification Performance
• 4.1 Lessons Learned from User Evaluation -- 4.2 Reviewer's Evaluation Lessons and Recommendation -- 5 User Interface Design Considerations and Conclusion -- References -- Stable Word-Clouds for Visualising Text-Changes Over Time -- 1 Introduction -- 2 Background -- 3 Project &amp -- Data -- 4 Stable Word-Clouds -- 4.1 Naive Stable Word-Clouds -- 4.2 Stable Placement via Pairwise Orthogonality -- 4.3 Multi-segment Selection Ranges -- 5 Evaluation -- 5.1 Stability of the Layout Algorithm -- 5.2 Performance -- 6 Conclusion &amp -- Future Work -- References -- A Hierarchical Label Network for Multi-label EuroVoc Classification of Legislative Contents -- 1 Introduction -- 2 Related Work -- 2.1 EuroVoc Classifiers -- 2.2 Extreme Multi-label Classification -- 3 Data Collection -- 4 Hierarchical Label Attention Neural Network -- 5 Experimental Evaluation -- 5.1 Evaluation Metrics -- 5.2 Results and Discussion -- 6 Conclusions and Future Work -- References -- Can Language Inference Support Metadata Generation? -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Experimental Setting -- 3.1 Experimental Set-up -- 3.2 Evaluation of the Models -- 4 Conclusions and Future Work -- References -- Information Governance Maturity Assessment Using Enterprise Architecture Model Analysis and Description Logics -- Abstract -- 1 Introduction -- 2 Background -- 2.1 Ontologies -- 2.2 Description Logics -- 3 Automated Maturity Model Assessment -- 4 Demonstration Using an Information Governance Maturity Model -- 5 Conclusion -- Acknowledgement -- References -- Finding Documents Related to Taiwan in the Veritable Records of Qing Using Relevance Feedback -- Abstract -- 1 Introduction -- 2 Relevance Feedback Algorithms and Evaluations -- 3 System and Experiments -- 4 Some Results and Observations -- 4.1 Observation on Time Distribution -- 4.2 Observation on Person Names
• Intro -- Preface -- Organization -- Contents -- Long and Short Papers -- Coner: A Collaborative Approach for Long-Tail Named Entity Recognition in Scientific Publications -- 1 Introduction -- 2 TSE-NER: An Iterative Approach for Long-Tail Entity Extraction -- 2.1 Heuristic Filtering -- 3 Collaborative Crowd Feedback -- 3.1 Coner Document Analyser CDA -- 3.2 Coner Interactive Document Viewer CIDV -- 3.3 Coner Feedback Analyser CFA -- 4 Evaluation -- 4.1 Experiment 1: Human Feedback on Unfiltered Entities -- 4.2 Experiment 2: NER Performance -- 5 Related Work -- 6 Conclusion and Future Work -- References -- An Unsupervised Method for Concept Association Analysis in Text Collections -- 1 Introduction -- 2 Background -- 3 Survey on Unsupervised Analysis of Digital Collections -- 3.1 Related Work -- 3.2 Concluding Remarks -- 4 The Proposed Unsupervised KDT Process -- 5 Results -- 6 Principles for Quality Assessment of the Pipeline -- 7 Conclusion and Future Work -- References -- Linking Semantic Fingerprints of Literature - from Simple Neural Embeddings Towards Contextualized Pharmaceutical Networks -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Experimental Investigation -- 3.1 Relationship Between Corpus-Data and Existing-DDAs -- 3.2 Relationship Between Corpus-Data and Predicted DDAs -- 3.3 Learning Dynamic Thresholds for K-NDNs -- 4 Conclusions -- References -- Learning to Rank Claim-Evidence Pairs to Assist Scientific-Based Argumentation -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Approach and Problem Formulation -- 3.1 Problem Formulation -- 3.2 Model -- 3.3 Domain Knowledge -- 3.4 Prestige Representation -- 3.5 Papers Rhetoric's -- 3.6 Embeddings -- 4 Experimental Setup -- 4.1 Data Description -- 4.2 Results and Discussion -- 5 Summary and Outlook -- References
• 3.2 Semantic Query -- 4 Semantic Query Framework -- 5 Exploration Tasks and Semantic Queries Conversion -- 5.1 Similar Entities -- 5.2 Similar Entities with Bias -- 5.3 Analogy Query -- 5.4 Analogy Browsing -- 6 Conclusion -- References -- The Memento Tracer Framework: Balancing Quality and Scalability for Web Archiving -- 1 Introduction and Motivation -- 2 Related Work -- 3 Memento Tracer Framework -- 3.1 Framework -- 3.2 Pilot -- 4 Experiment Design -- 4.1 Data Gathering -- 4.2 Traces for Dataset Resources -- 5 Experiments and Results -- 5.1 Archival Quality -- 5.2 Quality at Scale -- 5.3 Memento Tracer Overhead -- 6 Discussion and Future Work -- 7 Conclusion -- References -- The Immigration Dilemma -- Legal, Ethical and Practical Issues in Creating a Living, Growing Archive -- Abstract -- 1 Background -- 2 Copyright and Consent -- 3 Privacy and Safety -- 4 Metadata -- 5 Discussion -- 6 Conclusion -- References -- Segmenting User Sessions in Search Engine Query Logs Leveraging Word Embeddings -- 1 Introduction -- 2 Related Work -- 3 Unsupervised Segmentation of User Sessions -- 3.1 Individual Heuristics and Ablated Approaches -- 3.2 The Proposed Approach -- 4 Experimental Evaluation -- 4.1 Dataset and Experimental Methodology -- 4.2 Experimental Results -- 5 Conclusions and Future Work -- References -- A Human-Friendly Query Generation Frontend for a Scientific Events Knowledge Graph -- 1 Introduction -- 2 Related Work -- 3 Design Principles -- 4 Architecture -- 5 Use Cases -- 6 Implementation and Evaluation -- 7 Conclusions and Future Work -- References -- User Interface for Interactive Scientific Publications: A Design Case Study -- Abstract -- 1 Introduction -- 2 Background and Related Work -- 3 Case Study -- 3.1 User Interface Design Based on a Cognitive Framework -- 3.2 Method -- 4 Results and Discussion
• 5 Impact of Annotation Quality on Person Identification -- 5.1 Experimental Setup -- 5.2 Results -- 6 Conclusions -- References -- Who is Mona L.? Identifying Mentions of Artworks in Historical Archives -- 1 Artwork Mentions in Historical Archives -- 2 Named Entity Recognition for Artworks -- 3 Related Work -- 4 Annotating Complex Named Entity Types -- 5 Evaluation -- 6 Conclusion -- References -- Gatekeeper: Quantifying the Impacts of Service to the Scientific Community -- 1 Introduction -- 2 Related Work -- 2.1 Quantifying the Impacts of Research -- 2.2 Quantifying the Impacts of Scholars -- 3 Quantifying the Impacts of Service -- 4 Data Collection -- 4.1 STEP 1: Finding Conference Websites -- 4.2 STEP 2: Finding TPC Webpages -- 4.3 STEP 3: Scraping Gatekeepers -- 4.4 STEP 4: Scraping Research Keywords -- 5 Prototype Gatekeeper -- 5.1 Querying Gatekeepers -- 5.2 Querying Conferences -- 5.3 Querying Research Keywords -- 5.4 Other Applications of Gatekeeper -- 5.5 Future Work -- 6 Conclusion -- References -- A Study on the Readability of Scientific Publications -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Datasets -- 3.2 Examined Readability and Impact Measures -- 4 Results and Discussion -- 4.1 Longitudinal Study of Readability -- 4.2 Readability Measures Vs Expert Judgments -- 4.3 Abstract Readability vs Paper Impact -- 5 Conclusion -- References -- Interdisciplinary Collaborations in the Brazilian Scientific Community -- 1 Introduction -- 2 Data Acquisition and Preparation -- 3 Analysis of the Networks -- 4 Conclusions and Future Work -- References -- Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space -- 1 Introduction -- 2 Related Work -- 2.1 Knowledge Graph for Scholarly Data -- 2.2 Knowledge Graph Embedding -- 2.3 Word Embedding -- 3 Theoretical Analysis -- 3.1 The Semantic Structures of CP h
• 4.3 Observation on Place Names