CAMeRA

Project Overview

 

The Creative Industry Scientific Programme(CRISP) will develop a knowledge infrastructure which consolidates the leadership position and stimulates the continuing growth of the Dutch Design Sector and Creative Industries.

 

The research project Semantics of History develops a historical ontology and a lexicon that are used in a new type of information system that can handle the time-based dynamics and varying perspectives in historical archives more...

 

The goal of DutchSemCor is to deliver a one-million word Dutch corpus that is fully sense-tagged with senses and domain tags from the Cornetto database (STEVIN project STE05039). 250K words of this corpus will be manually tagged. The remainder will be automatically tagged using three different word-sense-disambiguation systems (WSD), and will be validated by human annotators. The corpus data will be based on existing corpus material collected in the projects CGN, D-CoI and SoNaR. These corpora have already been automatically annotated with morpho-syntactic tags and structures. The corpora will be extended where necessary to find sufficient examples for meanings of words that are less frequent and do not appear in the above corpora. The resulting corpus, for which we aim to offer the same balance in types of text as these basic resources, will be extremely rich in terms of lexical semantic information. Its availability will enable many new lines of research and technology developments for the Dutch language. In particular, it will enable research into the relation between language form and language interpretation, and as such it will be applicable in the fields of cognitive science, (psycho-)linguistics, language learning and language teaching, semantic web applications, information retrieval, machine translation, text mining, and document interpretation (summarization, topic segmentation). We foresee that the corpus will create new directions of research and technology development on a par with current developments for English.
Projectmanager: prof. Dr. Piek Vossen / Partners: UVA Amsterdam en Universiteit van Tilburg,  kickoff per september 2009.

The Amsterdam-Bijlmer Care Center (ABCC) is a building project in the South East of Amsterdam to upgrade the area with a center for short-term care. Within 4 years time, 300 apartments will be realized - more...

 

Applied Natural Language Processing, with Irion Technologies; Prof. P. Vossen;

Automated word-sense disambiguation in news texts in English and Spanish (‘SemEval’), text mining in scientific, company and news web pages in 6 European languages, dialogue systems in local authority websites in Dutch and English, and text complexity measurement in government and business texts in Dutch and English (Bureau Taal, ‘Texamen’); objective testing and commercial success. Spoken and web-based dialogue system on open unstructured data sets, GemeenteConnect. Sentiment analysis in textual sources and human-computer-interaction.

 

Communication advice and conversational practice in institutional settings

Drs. K.Y.Sliedrecht, Dr. M.L. Komter, Dr. F. van der Houwen, Drs. M.C.G. Schasfoort, Prof. W. Spooren (supervisor). Relation between communication advice and conversational practice in three institutional settings: police interrogations, job interviews, and journalistic interviews.

 

VU-Ster (programme ‘Communication, Text, and Culture: Rhetorical Devices in Public Communication’, with FPP and FSW); Prof. W. Spooren and Prof. G. Steen (supervisors), Drs. T. Pasma and Drs. K. Vis. Linguistic characterization of various genres in written and spoken media: metaphor and subjectification in Dutch news texts and conversations. - more...

 

To make a robot that emotionally is more human-like, it should be capable of balancing simultaneously occurring tendencies of positive and negative affect. - more...

 

‘A semantic database for Dutch’ (Taalunie, Stevin); Prof. P. Vossen, Drs. I. Maks, R. Segers, Dr. H. Van der Vliet.A Combinatoric and Relational Network for Language Technology": the extension of the Dutch wordnet with combinatoric and referential relations based on usage of words within domains. Cornetto is an initiative of Vossen and the Free University of Amsterdam to combine the Dutch wordnet and the Referentie Bestand Nederlands (a Dutch database with combinatoric information of Dutch word meanings) in a unique resource for Dutch. Cornetto will build a lexical semantic database for Dutch with rich vertical and horizontal semantic relations and combinatorial lexical constraints such as multiword expressions, idioms and collocations on the one hand, and lexical functions and frames on the other. The concepts will be aligned with the English Wordnet so that ontologies and domain labels can be imported. The semantic layer will be validated with a formal ontology, to make it usable in Semantic Web environments. Cornetto will cover 40K entries, including the most generic and central part of the language. The database goes beyond the structure and content of Wordnet and FrameNet. - more...

 

Over the last decade, the Internet has migrated people’s lives and homes and revolutionized the way people communicate with each other. Research suggests that the Internet affects people’s relationships with their closest partners in many ways. Its impact on marriages and couples, however, is uncharted territory. more...

Discovery is a festival for live music, live scientific research, DJs, VJs, cocktails, film, installations, performances, experiments, visuals, games, and presentations. - more...

 

Expertise center for terminology (Taalunie)

Dr. H. van der Vliet, 1 Research Assistant; construction of terminology system, with special reference to government language, in Dutch; system plus website, with strong connections to the AI department as well. - more...

 

Jean-Louis van Gelder, NSCR. CAMeRA and NSCR are partnering to see how young repeat-offending criminals see themselves and the future. Participants will confront future versions of themselves by being immersed in a high-quality three-dimensional environment, using a head-mounted display. more...

 

Dr. M. van den Haak, Prof. M. Hannay, Drs. L. Tavecchio, Dr. D. Torck. Linguistic characterization of various genres in written media: evaluation of user friendliness of local authority web texts, in Dutch and English; information packaging and rhetorical patterns in news texts, academic texts, and fiction texts, in Dutch and English; information packaging and rhetorical patterns in news texts in Dutch, German and French.

 

CAMeRA is part of the European Network of Excellence working on Integrated Research in Interactive Storytelling (IRIS). The IRIS consortium, composed of 10 partners from 7 different countries, aims to achieve breakthroughs in the understanding of Interactive Storytelling and the development of corresponding technologies. The project integrates disciplines of Artificial Intelligence, Cinematography, Animation, Authoring and Evaluation. more...

The iMG is of particular interest to researchers and companies that want to use games as unobtrusive measurement tools of attitude and user behavior to gain new insights in the area of imaging, population segmentation, assessment, recruitment, and community building. - more...

 

NWO-programme, Drs. T.C. van Charldorp, MPhil, Dr. F. Van der Houwen, Dr. M. Komter (PI), Dr. P. Sneijder, Prof. W. Spooren (supervisor). Linguistic characterization of various genres in written and spoken media: the interrelations between talk and written documents in Dutch police interrogations and criminal trials.

 

7th Framework Project in the area of Digital Libraries, Prof. P. Vossen. Conceptual modeling of knowledge related to expression in language, which involves, among others, the characterization of various genres in written and spoken media, across languages: cross-lingual and cross-cultural knowledge. The ultimate goal is to develop a knowledge and information transition system that is applied to the domain of the environment, in Dutch, English, Italian, Spanish, Chinese, Japanese; this Special Project constitutes a highly advanced contribution to the development of the Media Center of CAMeRA, linking text to meaning across cultures and genres. - more...

 

NWO-Vici programme, Prof. G. Steen (PI), A.G. Dorst, MA, J. Herrmann, MA, Drs. A. Kaal, T. Krennmayr, MA. Linguistic characterization of various genres in written and spoken media: metaphor in English news texts, academic texts, fiction texts, and conversations. - more...

 

CAMeRA participates in the EU funded project Metaverse1 to help provide a standardized global framework that enables the interoperability between virtual worlds (as for example Second Life, World of Warcraft, IMVU, Google Earth and many others) and the real world. - more...

 

Network Media Handling

CAMeRA collaborates with the NTNU in Norway to integrate 3D rendering and advanced distribution models with perceptual evaluation and management. A user perspective to VR will be taken that focuses on social computing, user participation, - more...

 

NextGen Virtual Reality
To make the use of IVR successful, designers must understand what potential users want and what they expect. Research in (I)VR has often focused on specific technological aspects, e.g. image resolution, action possibilities, but has not paid attention to the hopes and fears of users towards the use of IVR. - more...

 

T2PP combines contemporary theories and methods in linguistics with political science to develop an automated research tool for rich text-mining and opinion-mining - more...

 

The CAMeRA has set out to create a next generation virtual-reality research lab. This facility will use a state of the art 3D Engine and Virtual Reality hardware to drive its "VR Stations" and "Virtual Room." Both forms of virtual reality allow the users to develop and use software - more...

 

Web surveys
Traditional methods slowly become outdated. Response rates are declining, the consumer is less willing to participate, the research is expensive (money and time wise), - more...