Call for Papers (Deadline extended to 28th Feb)

1st International Workshop on Artificial Intelligence for Historical Image Enrichment and Access (AI4HI-2020).

AI4HI-2020 is a major forum that will bring together participants from various disciplines to present, discuss, disseminate and share insights on the exploitation of AI techniques, semantic web technologies and language resources for the semantic enrichment, search and retrieval of cultural images. The workshop will be co-located with the 12th Edition of  Language Resources and Evaluation Conference at the Palais du Pharo, Marseille, France.

Co-located with LREC-2020

Many historical, socio-cultural and linguistic research centres, national archives and museums are adopting open-access policies to promote efficient utilisation of their resources by the general public. However, much of the legacy data lacks detailed semantics and annotation beyond a title and a short description to be used and exploited by non-expert users and to be discovered by automated agents. Semantic web technologies are capable of enriching the data with the required semantics; however, existing ontologies and available models do not fully support the domain-specific requirements of users. As institutions plan to make historical images accessible to the general public, more and more domain-specific semantics will become available and linking such data in the LOD cloud by employing state-of-the-art AI techniques is attracting significant attention.

The AI4HI-2020 workshop has a general focus on the application of artificial intelligence, semantic web technologies such as ontologies, thesauri and controlled vocabularies, and language resources to enrich and improve access to images related (but not limited) to historical and cultural heritage. This workshop will provide the platform to discuss research results including experiments, use cases, experiences, best practices, methods and recommendations for the use of AI and semantic web technologies for historical images. The workshop will also bring various stakeholders including AI researchers, NLP experts, digital humanists, linguists, computer scientists and ontology engineers together to present their work and share their experiences.

Topics of Interest

We are interested in a wide range of artificial intelligence and semantic web topics which are of relevance for historical image enrichment, including language resources for image tagging, enrichment, interlinking, search and retrieval by employing semantics and AI technologies. The topics of interest include, but are not limited to:

1. Representation and modelling of cultural, historical and legacy image collections

  • Semantic modelling and representation of legacy Linked Open Data (LOD) for image enrichment.
  • Ontologies for cultural image description, image classification etc.
  • Semantic representation of aspects of image resources.
  • Semantic annotation, enrichment and use of multilingual description of images, paintings, photographs, etc.

2. Applications of semantic web technologies and linguistic resources for images collections

  • The use of semantic web technologies to annotate and enrich historical, cultural images, heritages, resources etc
  • The use of AI for efficient search and retrieval of historical, cultural and legacy images, heritages, resources etc
  • The use of domain-specific ontologies, thesaurus, dictionaries to enhance the organisation, retrieval and use of historical, cultural and legacy collections

3. Interoperability and interlinking of LOD for image resources 

  • Applications supporting interoperability and interlinking of legacy image collections from different public and private collections
  • Research incorporating rich semantics to the description of images 
  • Research supporting the generation and use of semantic interlinking of aspects of historical and cultural images.

4. Methods and tools for developing multilingual LOD for image resources

  • Tools for extracting concepts from descriptions of historical, cultural images
  • Methods and tools utilising LOD for organising, searching and retrieval of images
  • Methods and tools for building a knowledge graph of images

We invite both long and short papers representing original research, and novel approaches. Long papers up to 8 pages and additional 2 pages of reference and short papers up to 4 pages and 2 pages of references formatted according to the LREC 2020 guidelines are welcome. Short papers may also present project descriptions, early-stage research that has not yet been implemented and position papers.

Important Dates

  • Friday, Feb 28, 2020: Extended Submission deadline
  • Feb 21, 2020: Submission deadline
  • Mar 13, 2020: Notification of acceptance
  • Apr 02, 2020:  Camera-ready version
  • May 16, 2020: Workshop

Submission Details

Papers should be formatted according to the LREC stylesheets, and should be either 8 pages (plus 2 pages of references) for long papers or 4 pages (plus 2 pages of references) for short papers. Please submit your papers using SoftConf paper submission site

Format of the Workshop

The AI4HI workshop consists of 15/25 minute oral presentations, each followed by 5 minutes discussion time. 

Organising Committee

  • Yalemisew Abgaz, Adapt Centre, Dublin City University
  • Amelie Dorn, Austrian Academy of Sciences, Vienna, Austria
  • Jose Luis Preza, Diaz Austrian Academy of Sciences, Vienna, Austria
  • Gerda Koch – AIT Forschungsgesellschaft mbH, Europeana Local AT

Program Committee

  • Yalemisew Abgaz, Adapt Centre, Dublin City University
  • Amelie Dorn, Austrian Academy of Sciences, Vienna, Austria
  • Jose Luis Preza, Diaz Austrian Academy of Sciences, Vienna, Austria
  • Gerda Koch – AIT Forschungsgesellschaft mbH, Europeana Local AT
  • Renato Rocha Souza, Austrian Academy of Sciences, Vienna, Austria
  • Eveline Wandl-Vogt, Austrian Academy of Sciences, Vienna, Austria
  • Anna Fensel – Semantic Technology Institute (STI), University of Innsbruck, Austria
  • John Roberto, Adapt Centre, Dublin City University
  • More to appear

Identify, Describe and Share your LRs!

  • Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web-services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository.  This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data.
  • As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC 2020 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.