AccueilExploration, Navigation and Retrieval of Information in Cultural Heritage

*  *  *

Publié le mardi 21 mai 2013 par Elsa Zotian

Résumé

A key challenge facing the curators and providers of digital cultural heritage worldwide is to instigate, increase and enhance engagement with their collections. To achieve this, a fundamental change in the way these artefacts can be discovered, explored and contributed to by users and communities is required. Cultural heritage artefacts are digital representations of primary resources: manuscript collections, paintings, books, photographs etc. The text-based resources are often innately "noisy", contain non-standard spelling, poor punctuation and obsolete grammar and word forms. The image-based resources often have limited associated metadata which describes the resources and their content. In addition, the information needs and tasks of cultural heritage users are often complex and diverse. This presents a specific set of challenges to traditional Information Retrieval (IR) techniques and approaches. This workshop will investigate the enhanced retrieval of, and interaction with, cultural heritage collections.

Annonce

Presentation

Enrich 2013 has three main goals:

  • to discuss the challenges and opportunities in Information Retrieval research in the area of Cultural Heritage
  • to encourage collaboration between researchers engaged in work in this specialist area of Information Retrieval, and to foster the formation of a research community
  • to identify a set of actions which the community should undertake to progress research in this area
A key challenge facing the curators and providers of digital cultural heritage worldwide is to instigate, increase and enhance engagement with their collections. To achieve this, a fundamental change in the way these artefacts can be discovered, explored and contributed to by users and communities is required. Cultural heritage artefacts are digital representations of primary resources: manuscript collections, paintings, books, photographs etc. The text-based resources are often innately "noisy", contain non-standard spelling, poor punctuation and obsolete grammar and word forms. The image-based resources often have limited associated metadata which describes the resources and their content. In addition, the information needs and tasks of cultural heritage users are often complex and diverse. This presents a specific set of challenges to traditional Information Retrieval (IR) techniques and approaches.
 
This workshop will investigate the enhanced retrieval of, and interaction with, cultural heritage collections. We are interested in investigating innovative forms of personalised, multi-lingual IR, which can include: 
  • IR approaches tailored to cope with the inconsistencies which are common in cultural heritage collections.
  • Content-aware retrieval approaches which respond to the entities and relationships contained within artefacts and across collections.
  • Personalised IR and presentation.
  • Community-aware IR approaches which respond to community activity, interest, contribution and experience.
Such new forms of enhanced IR require rigorous evaluation and validation using appropriate metrics, contrasting digital cultural heritage collections and diverse users and communities. This workshop welcomes submissions which investigate such evaluation, taking into account the specific requirements of the domain. The nature of cultural heritage resources means that content analysis in support of IR is of specific interest. This includes the automated normalisation of historical texts, the use of Natural Language Processing (NLP) for entity extraction and metadata generation.
The ENRICH workshop aims to promote the exchange of ideas between researchers working on the theory and foundations of IR, cross and multi-lingual IR, personalised IR and recommender systems.

There are numerous research areas that can support such improved retrieval and exploration in the area of cultural heritage. Topics of interest include, but are not limited to, the following areas:

  • Multilingual semantic search
  • Context-aware and semantic recommender systems
  • Adaptation engines and algorithms for personalised multilingual IR
  • User modeling and adaptation (e.g. creation and exploitation of individual or stereotypical user profiles)
  • Content personalisation and personalised result presentation (e.g. beyond the ranked list)
  • domain modeling
  • External knowledge resources for IR (e.g. ontologies)
  • Evaluation methodologies and metrics for personalised multilingual IR
  • Information Extraction, Data Mining and Natural Language Processing
  • Social Network Analysis

Submission guidelines

We invite researchers to submit two categories of paper: 

  • Long paper submissions should report on substantial contributions of lasting value. Each accepted long paper will be presented in a plenary session of the workshop program. The maximum length is 8 pages. 
  • Short paper submissions should discuss exciting new work that is not yet mature enough for a long paper. The presentation may include the demonstration of a system. The maximum length is 4 pages. 

Accepted papers will be published in the proceedings of the workshop.

All submissions should be prepared according to the ACM SIG Proceedings Templates, as for all SIGIR submissions. For your convenience, you can use the templates for Microsoft Word or LaTeX that have been made available on the ACM website: http://www.acm.org/sigs/publications/proceedings-templates/

The ENRICH Workshop does not use blind reviews, so please include authors' names and affiliations on your submission. All submissions will receive several independent reviews. 

Submissions must be in PDF format and must be in English. 

All papers must be submitted electronically through the EasyChair submission page: https://www.easychair.org/conferences/?conf=enrich2013

before the 9th of June 2013

Schedule

  • Deadline for submission: 9th June
  • Notification of acceptance:28th June
  • Camera-ready version of papers: 8th July
  • Workshop: 1st August

Programme Committee

  • Leif Azzopardi (Glasgow University, Scotland)
  • Federica Cena (University of Turin, Italy)
  • Nicola Ferro (University of Padua, Italy)
  • Gareth Jones (Dublin City University, Ireland)
  • Udo Kruschwitz (University of Essex, Essex, UK)
  • Doug Oard (University of Maryland, US)
  • Dong Zhou (Hunan University of Technology, China)

Organisers

  • Prof. Séamus Lawless (School of Computer Science, Trinity College Dublin, Ireland)
  • Prof. Maristella Agosti (Department of Information Engineering, University of Padova, Italy)
  • Dr. Paul Clough (Information School, University of Sheffield, UK)
  • Prof. Owen Conlan (School of Computer Science, Trinity College Dublin, Ireland)

Lieux

  • Long Room Hub - Trinity College Dublin, College Green, Dublin 2
    Dublin, Irlande

Dates

  • dimanche 09 juin 2013

Mots-clés

  • Information Retrieval research, cultural heritage

Contacts

  • Seamus Lawless
    courriel : seamus [dot] lawless [at] scss [dot] tcd [dot] ie

URLS de référence

Source de l'information

  • Ele Kraft
    courriel : gkraft [at] gcdh [dot] de

Pour citer cette annonce

« Exploration, Navigation and Retrieval of Information in Cultural Heritage », Appel à contribution, Calenda, Publié le mardi 21 mai 2013, http://calenda.org/248629