Project Name | Start Date | End Date |
---|
Arts, Media and Culture | 2006-07-01 | - |
- Description
- The aim of the Arts, Media and Culture (AMC) programme is to analyse the dynamics of cultural transformation by studying how developments in the arts and the media respond to socio-cultural and political changes and how vice versa cultural artifacts and practices can shape social and political culture. AMC researchers study the whole spectrum of high-brow, middle-brow and low-brow culture, ranging from poems to installation artworks, from political essays to public monuments, from social media to performance art and from digital games to Limburg Carnival. What unites these inquiries is a focus on the practices in which cultural artifacts are produced, distributed and received. AMC research continues to analyse and interpret the meaning of cultural objects as ‘texts’, but increasingly this research includes the sites of their production, reception and/or co-creation: the classrooms where children’s literature is taught, the museum storage rooms where installations are stored and conserved, the supermarkets where dialect is spoken, the elderly homes where clowns perform with people with dementia or the virtual communities where game or music enthusiasts share fan productions. This emphasis on situated practices means that we are interested in the social and historical, but also in the material and bodily constituents of culture-in-the-making.
- Disciplines
- Social History
- Institutions
Research Institute for Arts and Social Sciences Maastricht (Secretariat) - Persons
Prof.dr. R. van de Vall (Project leader)
|
Asymmetrical Encounters – Digital Humanities Approaches to Reference Cultures in Europe, 1815-1992 | 2012 | 2016 |
- Description
- This project will explore the cultural aspects of European identity and how the reference cultures have changed between 1815-1992. The project members will use large volumes of textual materials, largely in the form of long runs of digitized newspapers, pamphlets etc., and apply multi-lingual text mining techniques to explore intercultural references across time and space.
- Disciplines
- History
Cultural Studies
- Institutions
Humanities in the European Research Area (HERA) (Financier) Trier University (Collaboration) University College London (Collaboration) - Persons
J. van Eijnatten (Project leader)
|
Audiovisual prosody in interaction | 2003-01-01 | 2008-10-01 |
- Description
- This research proposal is concerned with a functional approach to verbal and visual prosody in spoken conversations. The problem to be addressed in the project is about the combined use of specific auditive cues (such as intonation, tempo, voice quality and pausing) and specific visual cues (such as facial expressions and specific body gestures) for marking different dialogue phenomena. First, we will explore how audiovisual prosody can be exploited to highlight the information status of words. Then, we will investigate how it can be used to signal whether or not the process of information exchange in a dialogue is going well. Next, we will explore how it can support the turn-taking mechanism in spontaneous interactions. Finally, we will see to what extent audiovisual prosody may reflect speakers emotions and attitudes. The results of these different substudies will be integrated in one coherent, functional model of audiovisual prosody. All the questions will be tackled from the point of view of both the speaker and the listener, and from a crosslinguistic perspective. Insight into functional aspects of audiovisual prosody is relevant from both a theoretical and applied perspective. First, it is remarkable to observe that this important communicative device is still largely unexplored. Knowledge about how audiovisual prosody works may yield new insights into how people mark important words, deixis, turn-taking, discourse structure, etc. and more general into how languages can differ in the way they signal linguistic and paralinguistic phenomena. Second, there is an increasing interest in computer interfaces that rely on what is termed embodied conversational agents , i.e., specific software components that appear to users as animated characters. To make these agents believable and communicative , it is important to know in full detail how specific auditive and visual parameters contribute to speech communication. (Keywords: audiovisual prosody, dialogue analysis, speech technology, embodied conversational agents).
- Disciplines
- -
- Institutions
NWO Council for the Humanities (Financier) Department of Culture Studies Tilburg (Secretariat) - Persons
Drs.ing. L. van de Laar (Researcher) Prof.dr. E.J. Krahmer (Supervisor) Prof.dr. M.G.J. Swerts (Supervisor) Dr. P.N. Barkhuysen (Doctoral/PhD student)
|
Augmenting Masterpieces: Interfaces between the Psysical and Digital Collection of the Rijksmuseum | 2013 | 2014 |
- Description
- This research project aims at creating a theoretical framework, formulating existing and desired features, testing user experience, developing prototypes of new interfaces for virtual and physical interaction in the museum context and creating a final product to be used for augmented museum tours.
- Disciplines
- Heritage Studies
- Institutions
Rijksmuseum Amsterdam (Collaboration) - Persons
- -
|
Automated Detection of Financial Events in News Text | 2009-01-01 | 2014-12-01 |
- Description
- The current financial markets are inextricably linked to financial events like acquisitions, earnings announcements or product launches. Information distilled from news articles that deal with such events could therefore be useful in making financial decisions. However, the huge amount of daily news makes a manual analysis impossible. In addition, a (semi-) automated approach for discovering and applying financial events is difficult because of the unstructured nature of the textual data. For his dissertation examined how Hogenboom financial events can be detected in news articles and how they can be effectively used in financial applications. He presents a semi-automatic system to get financial events from the text of news. To do this, he developed in order to define an innovative extraction cartridges language, which may be applied to natural language. The knowledge-based system remains up to date because it is synchronized with the latest market developments through a newly developed language. As the underlying knowledge will automatically change with the discovered financial events. Hoogenboom also examined the practical usability of financial events. Experiments in the automated stock trading show that the best performing trade rules not only use traditional numerical signals (numbers), but also signals that originate from events that are mentioned in news articles. Moreover, the results of financial risk analyzes improve visible when use is made of data that has been cleaned of distortions, caused by financial events. According Hogenboom suggest such results, financial events of news articles can be used well as an additional factor in many financial applications.
- Disciplines
- Computer Science
Computational Linguistics Linguistics Information Science
- Institutions
NWO Council for Physical Sciences (Financier) Erasmus Research Institute of Management - ERIM (Secretariat) Erasmus Studio for E-research - Persons
Dr. F. Frasincar (Co-supervisor) Prof.dr. F.M.G. de Jong (Supervisor) Prof.dr.ir. U. Kaymak (Supervisor) Dr. F.P. Hogenboom (Doctoral/PhD student)
|
Automated historical judgement extraction: Analyzing perspectives on big and small heroes through NLP | 2015 | 2015 |
- Description
- This year, a movie about Michiel de Ruyter (1607-1676), the most famous admiral
from the Netherlands [1], was released. The fame of De Ruyter has inspired people
for centuries. De Ruyter was even voted number seven in the 2004 Dutch tv elections
for the grandest’ Dutch person from history [2]. A search in the Google Ngram viewer
shows that he also became increasingly known in the twentieth century in English
language books [3]. Not everyone, however, believes he should be venerated as a hero.
One group in particular, ‘Michiel de Rover’, protests against the movie and sees De
Ruyter as a sea robber who played a doubtful role in Dutch slavery practices (Jensen
2015, Historiek 2015; Elsevier 2010 for earlier controversy).
De Ruyter is a good example, and many more can easily be found, of how the perspective
on people changes over time and is dependent on social, cultural and political
factors. It is difficult however, to see patterns in how time tells a different story. Such
patterns are extremely interesting, because they could reveal a lot about historiography
and identity. What attributes do ‘heroes’, or villains, get from historians over time? Is
there a difference in the way women/men, politicians/painters, protestants/catholics
are described over time? What topoi do historians use? Are there any ‘national’ characteristics
discernible in historiographical sources? To answers such questions one
would have to ‘close read’ an incredible number of sources from the past. Much more
than any person could do in a reasonable amount of time. In this paper we apply
NLP (automatic text analysis) tools to have a computer aid us in this task. This paper
introduces our methodology and first results in using an NLP pipeline for automated
historical judgement extraction.
For our purpose we use two extensive biographical dictionaries from the nineteenth
and twentieth centuries to start with (Van der Aa 1852-1878, Blok and Molhuysen 1911-
1937). They contain circa 45,000 short biographies on famous Dutch people from all
history. There is a lot of overlap in the people described, which makes comparisons
possible. Our approach in using NLP to mine perspectives from these texts is twofold.
First, we analyze a relatively small selection of texts manually on positive and negative
character traits which were attributed to people’s characters and their deeds by the
authors of the texts and by third parties mentioned in the texts. Second, we use an
NLP pipeline that aims to identify positive and negative traits automatically. It is
based on an existing pipeline that was originally built for event extraction, including
a Named Entity Recognizer [4]. In this paper, we will introduce our methodology in
oral presentations 19
more detail, present the results (precision and recall) from our pipeline and will discuss
what (preliminary) answers we were able to give to the kind of questions asked in the
second paragraph.
- Disciplines
- History
- Institutions
Vrije Universiteit Amsterdam - Persons
M.P. Groten (Researcher) M.Y. Karimi (Student Assistant ) Dr. S. ter Braake (Researcher) MSc A.S. Fokkens (Researcher)
|
Automatic speech recognition for Dutch dysarthric speech: a pilot study | 2000-01-01 | 2003-12-01 |
- Description
- The goal of this pilot study was to conduct a feasibility study into automatic speech recognition (ASR) of Dutch dysarthric speech. To find out to what extent ASR can be used to the benefit of dysarthric speakers, we intended to answer the following questions: * How well can dysarthric speech be recognised by a continuous speech recogniser (CSR) trained on non-dysarthric speech? * Will the recognition results improve if we train the CSR on (a limited amount of) speech of dysarthric speakers? * To what level of complexity are automatic recognition tasks of dysarthric speech feasible with current ASR technology? - Methodology: We conducted a series of experiments for which we used read speech of two dysarthric speakers and two non-dysarthric (reference) speakers. All speakers read numbers, frequent utterances, semantically unpredictable sentences and phonetically rich sentences. For recognition a standard phone-based CSR was used. Results of the recognition experiments were presented as word error rates, i.e. the number of substitutions, insertions and deletions dived by the total number of words. Performance of the CSR was tested by using speaker independent models, speaker dependent models (using a jack-knife procedure) and by extending the size of the lexicon and the amount of training material. - Results: Word error rates ranged from 4.5% to 41.0% for dysarthric speech that is recognised with the CSR trained on non-dysarthric speech. Relative large improvements were found (50% to 100%) when the CSR was trained on speech of the dysarthric speakers. Results indicate that ASR of dysarthric speech is possible for low-perplexity tasks, i.e. when using a language model. ASR of dysarthric speech also seems promising for higher perplexity tasks, especially when speech rate of the speakers is relatively slow.
- Disciplines
- Speech technology
- Institutions
St. Martin Clinic (Secretariat) Radboud Universiteit Nijmegen - Persons
Prof.dr. L.W.J. Boves (Researcher) Prof.dr. A.C.M. Rietveld (Researcher) Prof.dr. A.C.H. Geurts (Researcher) P. Holtus (Researcher) Dr. J. van Limbeek (Researcher) Drs. E. Sanders (Researcher) M.B. Ruiter (Researcher) Dr. L.J. Beijer (Researcher) Dr. W.A.J. Strik (Project leader)
|
Automatic text analysis and machinelearning for prosody | 2001-01-01 | 2005-01-01 |
- Disciplines
- Linguistics
- Institutions
Department of Communication and Information Sciences Tilburg (Secretariat) Department of Communication and Information Science Tilburg - Persons
Dr. M.W.C. Reynaert (Project leader)
|
Bartholomeus Engelsman van den Proprieteyten der Dinghen | 2005 | 2010 |
- Description
- Een diplomatische editie van de Middelnederlandse vertaling (1485) van de 13de-eeuwse encyclopedie De proprietatibus rerum van Bartholomaeus Anglicus Bezorgd door de Werkgroep Middelnederlandse Artesliteratuur (WEMAL), in samenwerking met het Huygens Instituut KNAW, de Digitale Bibliotheek voor de Nederlandse Letteren en het Instituut voor Nederlandse Lexicologie.
A diplomatic edition of the Middle Dutch translation (1485) of the 13th century encyclopedia proprietatibus rerum Bartholomaeus Anglicus Concerned by the Working Group on Middle Dutch Arte Literature (WEMAL), in collaboration with the Huygens Institute, the Digital Library of Dutch Literature and the Institute for Dutch Lexicology.
- Disciplines
- Literary Studies
- Institutions
Huygens Institute for the History of the Netherlands (Collaboration) INL (Institute for Dutch Lexicology) (Collaboration) Universiteit Utrecht - Persons
N. Versélewel (Researcher) H. De Witt (Researcher)
|
Bayesian Music Transcription | 1997-09-01 | 2004-09-01 |
- Description
- Muziektranscriptie is het omzetten van een gedigitaliseerde opname van een muziekuitvoering in een beschrijving die te lezen en te begrijpen is. Transcriptie van iedere willekeurige muziekuitvoering zonder enige aanname van de soort muziek is een zeer moeilijk probleem. Het doel van het proefschrift van de heer Cemgil was om een praktische aanpak voor muziektranscriptie te ontwikkelen door een combinatie van kennis vanuit muziekwetenschap en akoestiek, en computationele technieken afkomstig uit de kunstmatige intelligentie.
Music Transcription is the conversion of a digitized recording of a musical performance in a description which is to read and understand. Transcription of any given music performance without any assumption of the kind of music is a very difficult problem. The aim of the thesis of Mr. Cemgil was to develop a practical approach to music transcription by combining knowledge from musicology and acoustics, and computational techniques derived from artificial intelligence.
- Disciplines
- Musicology
Computer Science
- Institutions
Donders Centre for Cognition (Secretariat) Radboud Universiteit Nijmegen Donders Centre for Cognition - Persons
Prof.dr. H.J. Kappen (Co-supervisor) P.J.T.M. Trilsbeek (Researcher) Prof.dr.ir. P.W.M. Desain (Project leader) Prof.dr. H.J. Honing (Project leader) Prof.dr. C.C.A.M. Gielen (Supervisor) Dr. A.T. Cemgil (Doctoral/PhD student)
|