AccueilMultilinguality in historical documents

Multilinguality in historical documents

Challenges and solutions for digital humanities (MHist)

*  *  *

Publié le lundi 02 juin 2014 par Elsa Zotian

Résumé

In the digital age the storage and visualisation of old texts should be accompanied by a collection of tools empowering the  text with suitable information and making it understandable for different user groups. Such tools usually involve automatic language processing methods. In contrast to processing of modern texts, for which language technology made a huge progress in the last years, automatic processing of old texts is still problematic. The focus of this workshop is on the adaptition of existing multilingual language resources and tools, and, where necessary, the development training data in the form of corpora or lexicons for a certain period of time in history.

Annonce

Full-day Workshop organised in conjunction with the Digital Humanities 2014 Conference (http://dh2014.org) 7 July 2014 Lausanne, Switzerland

http://www.linguistics.ruhr-uni-bochum.de/MHist/

Workshop endorsed by the ACL-SIGHUM Special Interest Group on Language

Technologies for the Socio-Economic Sciences and Humanities

(http://sighum.science.ru.nl/)

Argument

Recently, the collaboration between the Language Technology community and the specialists in various areas of the Humanities has become more efficient and fruitful due to the common aim of exploring and preserving cultural heritage data. It is worth mentioning the efforts made during the digitisation campaigns in the last years and within a series of initiatives in the Digital Humanities, especially in making old manuscripts and prints available in the form of Digital Libraries.

The availability of old texts on-line produced a revolutionary shiftin the way how such objects are analysed.  They are no longer restricted to a small number of specialists, knowing the language of the document but to broader groups with various requirements:

1. non-expert users who would like to know what the document is about, understand the main topics, localise places, persons. These users have no or very little knowledge of old languages, and usually are less familiarised with toponyms (especially when these belong to geographical spaces unknown to the user);

2. researchers of neighbor fields, who often have only minimal knowledge of the language but considerable knowledge of the historical context and might be familiarised with historical toponyms and proper names;

3. students and researchers specialising in historical data, who have the required language skills but still can profit from additional information accompanying the texts.

These considerations imply that the storage and visualisation of old texts should be accompanied by a collection of tools empowering the text with suitable information and making it understandable for different user groups. Such tools usually involve automatic language processing methods. In contrast to processing of modern texts, for which language technology made a huge progress in the last years, automatic processing of old texts is still problematic mainly because:

  • Historical language data is sparse. First, compared to the wealth of documents written in modern languages, there are only few documents available for historical languages. Second, transcribing old manuscripts often requires expert knowledge. Third, due to the absence of a standard language, historical language variants differ in spelling, morphology, syntax, and lexical semantics from each other.
  • Texts are often multilingual, consisting of mixtures of different languages, such as single words or phrases or entire sentences written in Latin that are intermixed with passages written in the actual language of the text. In case of texts from areas with rich cultural mixtures (e.g. Balkans), one can find in addition paragraphs in ?exotic? local languages.

The focus of this workshop is on the second aspect. We think that the challenges posed by multilinguality should be tackled by adapting existing multilingual language resources and tools, and, where necessary, by providing training data in the form of corpora or lexicons for a certain period of time in history.

We are looking for original unpublished work in one of the following topics but not limited to:

  • character-level MT for normalisation
  • historical and modern data as comparable corpora
  • historical texts in different languages as parallel or comparable corpora
  • MT for translation between language versions
  • OCR for multilingual documents
  • word- and/or paragraph-level language identification
  • crosslingual retrieval in historical documents
  • ontologies as language-independent interfaces between collections of historical texts
  • particularities of multilingual historical texts and challenges for IT
  • information extraction and retrieval for multilingual historical documents

Submission guidelines

Authors interested in submitting a paper are required to send an email at cristina.vertan@uni-hamburg.de containing the title , the authors and 10 lines abstract

no later than 15th May.

Submissions are due to 10th of June in Form of an abstract of about 1500 words, at the same address.

Notifications of acceptance /rejection will be  issued around 25th of June.

Timeline

  • Intention email: 15th of May 2014
  • Submission of abstracts: 10th June 2014
  • Notification of acceptance / rejection  25th of June 2014
  • Workshop  7th July 2014

Programme committee

  • Lars Borin. (University of Gothenburg, Sweden)
  • Rafael Carrasco (University of Alicante, Spain)
  • Paul Doorenbosch (National Library of the Netherlands, Netherlands)
  • Thorhallur Eythorsson (University of Iceland)
  •  Alexander Geyken (BBAW, Germany)
  • Günther Görz (University Erlangen, Germany)
  • Walther v. Hahn (University of Hamburg, Germany)
  • Erhard Hinrichs (University of Tuebingen, Germany)
  •  Guillaume Jacquet (JRC, Italy)
  • Marc Kupietz (IDS, Germany)
  • Éric Laporte (Université Paris-Est Marne-la-Vallée, France)
  • Piroska Lendvai (Hungarian Academy of Sciences, Hungary)
  •  Thierry Paquet (LITIS, France)
  • Gábor Prószéky (MorphoLogic, Hungary)
  • Bente Maegaard (University of Copenhagen, Denmark)
  •  Christian Emil Ore (University of Oslo, Norway)
  •  Eiríkur Rögnvaldsson, (University of Iceland)
  •  Petya Osenova (IICT, Bulgarian Academy of Sciences, Bulgaria)
  •  Manfred Thaller (Cologne University, Germany, Germany
  •  Tamás Váradi (Hungarian Academy of Sciences, Hungary)
  •  Matthew Whelpton, (University of Iceland.)
  • Kalliopi Zervanou (University of Tilburg, the Netherlands)
  • ORGANISING COMMITTEE
  • Cristian Vertan, University of Hamburg, Germany
  • Stefanie Dipper, Ruhr-University Bochum, Germany
  • Noah Bubenhofer, TU Dresden, German / UZH Zurich, Switzerland
  • Laurent Romary, INRIA, France / Humbold-University Berlin, Germany

Dates

  • mardi 10 juin 2014

Mots-clés

  • digital humanites, multilinguality, language technology

Contacts

  • Vertan Cristina
    courriel : cristina [dot] vertan [at] uni-hamburg [dot] de
  • Romary Laurent
    courriel : laurent [dot] romary [at] inria [dot] fr

Source de l'information

  • Vertan Cristina
    courriel : cristina [dot] vertan [at] uni-hamburg [dot] de

Pour citer cette annonce

« Multilinguality in historical documents », Appel à contribution, Calenda, Publié le lundi 02 juin 2014, http://calenda.org/287139