supporting information management in digital libraries
play

Supporting Information Management in Digital Libraries with - PowerPoint PPT Presentation

Nov 18, 2022 •561 likes •883 views

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Supporting Information Management in Digital Libraries with Map-based Interfaces Rudolf Mayer , Angela Roiger, Andreas Rauber Vienna University of

  1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Supporting Information Management in Digital Libraries with Map-based Interfaces Rudolf Mayer , Angela Roiger, Andreas Rauber Vienna University of Technolgy http://www.ifs.tuwien.ac.at/~mayer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  2. Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Overview on Self-Organising Map – Principals • Maps of Digital Libraries – Systems – Interaction – Semantic description . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  3. Self-Organizing Map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Unsupervised neural network model • Topology-preserving mapping from a high to a low dimensional space • Offers cluster analysis, relationships • Overview over large, high-dimensional datasets • Scalable • Stable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23.11.2005 Semantics 2005 3

  4. Self-Organizing Map: Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Input & output space (vectors) (2D map) x 1 x 3 x 2 Modell/weight vectors n -dim. n -dim. Unit . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  5. Self-Organizing Map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Learning process – competitive learning x m(t+1) m(t) Input space Output space . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  6. Self-Organizing Map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Learning process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  7. Self-Organizing Map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Learning process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  8. Self-Organizing Map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Learning process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  9. SOMs in Digital Libraries . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1. Representation of Documents in Vector Space 2. Self-Organising Map training 3. Interface application • Several systems / applications – WEBSOM (Kohonen, IEEE TNN 2000) – SOMLib (Rauber, ECDL 99) – Newsmap (Chen, DSS 2005) – ... . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  10. SOMs in Digital Libraries . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Several systems / applications – However, not many real-world applications • Need for better methods/techniques for – User interaction with the map – Automatically describing and explaining the map to the user – Summarising the content / giving fast overview – Personalisation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  11. Novel map interaction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Integration of map-based interface with “traditional” Digital Library systems • Enables wealth of new ways of interaction – Highlight query results on the map – Select documents/regions on the map – Find related documents – Helps distinguishing results – Get an overview of the collection using the map • Small-scale user study with promising results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  12. Integration into Greenstone . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Map Search Search results Map selection Document list . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  13. System: Research documentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Digital Library of the Austrian Research • Combines ~15 universities in Austria in one central database • “Traditional” search via meta -data / full text • Alternative interface with Self-Organising Map – Visualisation of query results – Related documents – Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  14. System: Research documentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  15. Describing & explaining the map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Users want to get a quick overview of – Topics present in the collection – Their (relative) importance – Their correlations • Dominant approaches – Visualisation techniques to indicate cluster structures – does not reveal content – Labelling – static; mainly based on map-units . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  16. Describing & explaining the map . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Interactive & personalised approach to explore Digital Library contents: • Hierarchical clustering of the map to identify topical clusters/regions • Automatic labelling of clusters & sub-clusters • Summarisation of identified clusters • Interactive mode to “browse” through clusters • Personalisation through manual Labelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  17. Demo: 20 Newsgroups . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . • Benchmark Data set • 1000 Postings per newsgroup • Hierarchies of Newsgroups • Term indexing • SOM training • Hierarchical clustering (Ward’s clustering) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  18. Demo: 20 Newsgroups . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  19. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  20. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  21. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  22. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  23. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  24. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  25. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  26. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  27. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

  28. 20 Newsgroups: Cluster+Labels . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

* Pearl DeSure LIS 647 Systems Analysis for Information Management (with a focus on digital

* Pearl DeSure LIS 647 Systems Analysis for Information Management (with a focus on digital

* Pearl DeSure LIS 647 Systems Analysis for Information Management (with a focus on digital libraries) November 9, 2011 Dr. Luz M. Quiroga 1 * To select, collect, preserve and make accessible the accumulated wisdom of the world,

635 views • 11 slides
Digital Libraries and Development Hussein Suleman hussein@cs.uct.ac.za University of Cape Town

Digital Libraries and Development Hussein Suleman hussein@cs.uct.ac.za University of Cape Town

Digital Libraries and Development Hussein Suleman hussein@cs.uct.ac.za University of Cape Town Department of Computer Science Digital Libraries Laboratory @ Centre for ICT4D August 2015 The Challenge How do we build Digital Libraries to

772 views • 28 slides
scientific corpus HUI WEI Data collection Some digital libraries did not supply APIs We use raw

scientific corpus HUI WEI Data collection Some digital libraries did not supply APIs We use raw

Data mining, management and visualization in large scientific corpus HUI WEI Data collection Some digital libraries did not supply APIs We use raw PDF docs as input Data collection 1. to extract basic information of a paper such as authors,

418 views • 12 slides
Information Retrieval for Development Hussein Suleman Digital Libraries Laboratory @ Centre for

Information Retrieval for Development Hussein Suleman Digital Libraries Laboratory @ Centre for

Information Retrieval for Development Hussein Suleman Digital Libraries Laboratory @ Centre for ICT4D Department of Computer Science University of Cape Town January 2019 Key Research Question How do we use Information Retrieval / Data

577 views • 53 slides
1 Data and information services: Scientific data directories/ repositories/ portals :

1 Data and information services: Scientific data directories/ repositories/ portals :

General background Driving forces rapid evolution of : Digital Libraries Computing power hardware Memory Networking (internet) From Information retrieval to search engines DB systems e-books, e-libraries &

400 views • 4 slides
Information Retrieval and Filtering over Self-Organising Digital Libraries Paraskevi Raftopoulou

Information Retrieval and Filtering over Self-Organising Digital Libraries Paraskevi Raftopoulou

Information Retrieval and Filtering over Self-Organising Digital Libraries Paraskevi Raftopoulou Raftopoulou 1,2 1,2 , Euripides G.M. Petrakis 2 , Paraskevi Christos Tryfonopoulos 1 , and Gerhard Weikum 1 1 Max-Planck Institute for Informatics,

561 views • 32 slides
DAFFODIL Effective Support for Using Digital Libraries Norbert Fuhr University of

DAFFODIL Effective Support for Using Digital Libraries Norbert Fuhr University of

Distributed Agents for User-Friendly Access of Digital Libraries DAFFODIL Effective Support for Using Digital Libraries Norbert Fuhr University of Duisburg-Essen, Germany *Supported by DFG as part of the Research Programme V 3 D 2 1

487 views • 35 slides
Simple Archive Architectures Lighton Phiri and Hussein Suleman Digital Libraries Laboratory

Simple Archive Architectures Lighton Phiri and Hussein Suleman Digital Libraries Laboratory

Simple Archive Architectures Lighton Phiri and Hussein Suleman Digital Libraries Laboratory Department of Computer Science University of Cape Town IFLA '15 Workshop on Digital Libraries: research methods and tools www.martinwest.uct.ac.za 2

719 views • 24 slides
Digital Libraries Collaborative Filtering and Recommender Systems Week 12 Min-Yen

Digital Libraries Collaborative Filtering and Recommender Systems Week 12 Min-Yen

Digital Libraries Collaborative Filtering and Recommender Systems Week 12 Min-Yen KAN 26 Oct 2004 1 Information Seeking, recap Q2 T T T Q1 Q3 Q4 In information seeking, we may seek others opinion: Recommender

805 views • 37 slides
Digital Libraries@UC with DSpace/GLAM Universidade de Coimbra (since 1290, Portugal) Ana Lusa

Digital Libraries@UC with DSpace/GLAM Universidade de Coimbra (since 1290, Portugal) Ana Lusa

Digital Libraries@UC with DSpace/GLAM Universidade de Coimbra (since 1290, Portugal) Ana Lusa Silva, Ana Maria Miguis, Bruno Neves, Mrio Bernardes Joint Library Service UC (SIBUC) 13.Jun.2019 Digital Libraries@UC with DSpace/GLAM UC

487 views • 14 slides
Corpus Assembly as Text Data Integration from Digital Libraries and the Web Udo Hahn & Tinghui

Corpus Assembly as Text Data Integration from Digital Libraries and the Web Udo Hahn & Tinghui

Corpus Assembly as Text Data Integration from Digital Libraries and the Web Udo Hahn & Tinghui Duan Jena University Language & Information Engineering (JULIE) Lab https://julielab.de/ DFG Graduate School Romanticism as a Model

569 views • 27 slides
Supporting Data Interlinking in Semantic Libraries with Microtask Crowdsourcing Cristina Sarasua

Supporting Data Interlinking in Semantic Libraries with Microtask Crowdsourcing Cristina Sarasua

Supporting Data Interlinking in Semantic Libraries with Microtask Crowdsourcing Cristina Sarasua SWIB 2014, Bonn Institute for Web Science and Technologies University of Koblenz-Landau, Germany Cristina Sarasua Supporting Data

585 views • 33 slides
Supporting learners in the workplace new roles for libraries and librarians Presented by

Supporting learners in the workplace new roles for libraries and librarians Presented by

Supporting learners in the workplace new roles for libraries and librarians Presented by Shane Godbolt, NCGST and Dr Aileen Wood, London Deanery CHAIN and NHSU, Workplace based learning in the NHS. 8/9 December 2003 Dreaming the future

284 views • 12 slides
through Public Libraries Marianne Brennan Self Management Programme Health and Social Care

through Public Libraries Marianne Brennan Self Management Programme Health and Social Care

Promoting Health and Wellbeing through Public Libraries Marianne Brennan Self Management Programme Health and Social Care Alliance Scotland How do we use libraries? What are we going to do? The Scottish Library and Information Council has

430 views • 17 slides
INFORMATION MANAGEMENT AND DIGITAL GOVERNMENT David C.G. Brown School of Political Studies

INFORMATION MANAGEMENT AND DIGITAL GOVERNMENT David C.G. Brown School of Political Studies

1 February 6, 2015 Information Management and Digital Government INFORMATION MANAGEMENT AND DIGITAL GOVERNMENT David C.G. Brown School of Political Studies University of Ottawa Presentation at School of Public Policy and Governance

662 views • 22 slides
Lecture 4 Museums intro Patrick Schmitz i290-rmm Collection Management Systems the

Lecture 4 Museums intro Patrick Schmitz i290-rmm Collection Management Systems the

Lecture 4 Museums intro Patrick Schmitz i290-rmm Collection Management Systems the center of scholarly ecosystem Molecular Lab Digital Assets and Information Archives and Content Management Libraries Field Data Outreach and Data

612 views • 23 slides
A. Morrison, G. Ross,

A. Morrison, G. Ross,

A. Morrison, G. Ross, and M. Chalmers. Fast multidimensional scaling through sampling,

293 views • 4 slides
Pattern Analysis and Machine Intelligence Lecture Notes on Clustering (II) 2011-2012 Davide

Pattern Analysis and Machine Intelligence Lecture Notes on Clustering (II) 2011-2012 Davide

Pattern Analysis and Machine Intelligence Lecture Notes on Clustering (II) 2011-2012 Davide Eynard eynard@elet.polimi.it Department of Electronics and Information Politecnico di Milano p. 1/29 Course Schedule [ Tentative ] Date Topic

884 views • 52 slides
Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned

Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned

Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned into subsets (clusters), according to a similarity measure, such thatsimilardata is grouped into the same cluster. Unlabeled Data

442 views • 22 slides
Laterally Connected Lobe Component Analysis: Precision and Topography Matt Luciw Juyang Weng

Laterally Connected Lobe Component Analysis: Precision and Topography Matt Luciw Juyang Weng

Laterally Connected Lobe Component Analysis: Precision and Topography Matt Luciw Juyang Weng Embodied Intelligence Laboratory Department of Computer Science and Engineering Michigan State University East Lansing, MI Enabling Emergent Internal

382 views • 27 slides
G RAVITATIONAL C LUSTERING OF THE S ELF -O RGANIZING M AP Nejc Ilc Andrej Dobnikar University of

G RAVITATIONAL C LUSTERING OF THE S ELF -O RGANIZING M AP Nejc Ilc Andrej Dobnikar University of

ICANNGA 2011, Ljubljana G RAVITATIONAL C LUSTERING OF THE S ELF -O RGANIZING M AP Nejc Ilc Andrej Dobnikar University of Ljubljana Faculty of Computer and Information Science I NTRODUCTION Tools needed to deal with data/web mining

772 views • 28 slides
Data Warehousing and Machine Learning Preprocessing Thomas D. Nielsen Aalborg University

Data Warehousing and Machine Learning Preprocessing Thomas D. Nielsen Aalborg University

Data Warehousing and Machine Learning Preprocessing Thomas D. Nielsen Aalborg University Department of Computer Science Spring 2008 DWML Spring 2008 1 / 35 Preprocessing Before you can start on the actual data mining, the data may require

1.18k views • 84 slides
Machine Learning in Reservoir Production Simulation and Forecast Serge A. Terekhov NeurOK

Machine Learning in Reservoir Production Simulation and Forecast Serge A. Terekhov NeurOK

Machine Learning in Reservoir Production Simulation and Forecast Serge A. Terekhov NeurOK Techsoft, LLC, Moscow, Russia email : serge.terekhov@gmail.com Scaling Up and Modeling for Transport and Flow in Porous Media Dubrovnik, Croatia, 13-16

473 views • 14 slides
Machine Translation Research in META-NET Jan Haji Institute of Formal and Applied Linguistics

Machine Translation Research in META-NET Jan Haji Institute of Formal and Applied Linguistics

Machine Translation Research in META-NET Jan Haji Institute of Formal and Applied Linguistics Charles University in Prague, CZ hajic@ufal.mff.cuni.cz With contributions by Marcello Federico, Pavel Pecina, Stephan Peitz and Timo Honkela

274 views • 24 slides

More recommend