The Talk of Europe - Travelling CLARIN Campus project ( aims to instigate pan-European collaboration by organizing three international creative camps in 2014 and 2015. The first camp will be held on 6-10 October at the Netherlands Institute for Sound and Vision in Hilversum, the Netherlands.

The Talk of Europe (TOE) project is curating the proceedings of European Parliament (EP) from 1996 onwards, available in 21 languages, and converting these to RDF. Moreover, the data are enriched with biographical and political information on the speakers. Since the data are available in multilingual form, this dataset lends itself to be linked with resources in other European countries, such as parliamentary records or news reports. The RDF dataset and a SPARQL endpoint will be made available in September 2014.

The creative camp intends to bring together developers and academic researchers, with the goal of making inventive use of the EP dataset, exploiting web and natural language processing techniques to add new knowledge and functionality to the dataset. The goal is to develop proof-of-concept tools that can be applied in scholarly research in the political sciences and humanities.

The event will comprise five consecutive days, which will include:

  1. presentations by humanities scholars and political scientists on how they use political datasets
  2. presentations by computer scientists showing best practices from other projects
  3. practical sessions for tool development.


In order to participate, the TOE organisers welcome proposals describing ambitions for research tools and/or links with other datasets. Submissions should describe the following:

  • General description of idea (should not exceed 1000 words) including:
  • The research tool to be developed.
  • The datasets to be used.
  • The scholarly research problem or question to be addressed.
  • Contact info and a short description of research interests for all participants who would like to attend.
  • A work plan to indicate feasibility of proof-of-concept creation in 5 days.
  • A description of how the tool will be made available after the creative camp.

For inspiration, please see To submit a proposal, please send a docx or pdf file to 20 June 2014. Accepted proposals will be made available on


  • Participants must work in a European country. Proposals from developers and academic researchers from one of the following CLARIN ERIC member or observer countries are particularly welcome: Austria, Bulgaria, Czech Republic, Denmark, Estonia, Germany, The Netherlands, Norway, Poland, Dutch Language Union.
  • Participants are not required to have already been involved with CLARIN.
  • Master or PhD students, academics further in their career and non-academic developers are welcome.
  • Proposals that include international collaboration will be prioritized.
  • Datasets to be linked with the EP data may be from any type or source. Proposals with datasets available in are particularly welcome.
  • Proposals will be ranked to create a distribution of geography of participants, language and type of tools


  • Submissions due: Friday 20 June
  • Acceptance notification: Friday 27 June
  • Creative camp: Monday 6 - Friday 10 October 2014 (5 days)


The first creative camp will be held at Netherlands Institute for Sound and Vision in Hilversum, the Netherlands.


The TOE organisers will offer bursaries for all participants to cover all expenses of travel to the venue and staying in the hotel in the period of Sunday 5 until Saturday 11 October 2014.


Visit the website
For further information and questions, please contact Max Kemman ().

CLARIN meets Literature

24 april 2014, Göteborg, Sweden


Call for Papers (see the website)

The purpose of the series of ACL workshops on Computational Linguistics for Literature is to bring together researchers fascinated with literature as a unique type of data which pose distinct challenges. We invite papers on original unpublished work in this broad area. In particular, we hope to see papers which explore how the state-of-the-art NLP methods can help solve existing research problems in the humanities, or perhaps suggest new problems.

Literary texts revolve around the human condition, emotions, social life and inner life. Naturally, such data abound in common-sense knowledge but are very thin on technical jargon. Can tools and methods developed in the ACL community help process literary data? When do they work, when do they fail and why? What new instruments do we need in order to work with prose and poetry, on a large or small scale? Are there computational solutions of  noteworthy problems in the Humanities, Information Science, Library Sciences and other similar disciplines?

Here are some of the topics of interest to the workshop:

  • the needs of the readers and how these needs translate into meaningful NLP tasks;
  • searching for literature;
  • recommendation systems for literature;
  • computational modelling of narratives, computational narratology, computational folkloristics;
  • summarization of literature;
  • differences between literature and other types of writing as relevant to computational linguistics;
  • discourse structure in literature;
  • emotion analysis for literature;
  • profiling and authorship attribution;
  • identification and analysis of literary genres;
  • building and analyzing social networks of characters;
  • generation of literary narrative, dialogue or poetry;
  • modelling literary dialogue for generation.

We will consider regular papers which describe experimental methods or theoretical work, and we will gladly welcome position papers.
The NLP community does not study literature often enough, so it is important to discuss and formulate the problems before proposing solutions.

The submission deadline is January 23, 2014.

Anna Feldman, Anna Kazantseva, Stan Szpakowicz

Max Kemman will attend the Theory and Practice of Digital Libraries (September 22-26, Valetta, Malta) to present two posters and the workshop on Supporting Users Exploration of Digital Libraries (short, SUEDL2013) as well. The group (Max Kemman, Franciska de Jong, Stef Scagliola and Roeland Ordelman) submitted a demo paper titled Research Environment for Exploring Oral History Collections. In this paper they describe the fundamental principles underlying the CLARIAH-supported Oral History Today interface, which they are developing to improve exploration in oral history collections. To support scholars in their use of oral history collections, they draw upon the previous work of De Jong, Ordelman and Scagliola to describe four stages of scholarly research and user requirements related to each stage.

Read more on Max Kemman’s blog