- document
-
TNO Informatie- en Communicatietechnologie (author), Schavemaker, J.G.M. (author), Doets, P.J.O. (author), Bailer, W. (author), Stiegler, H. (author), Lee, F. (author), Neuschmied, H. (author), Kraaij, W. (author), Brandt, P. (author), Eendebak, P.T. (author), Ranguelova, E.B. (author), Thean, A.H.C. (author)In this document we report on existing technologies for video fingerprinting, audio fingerprinting, near duplicate detection and video linking inside and outside our consortium.report 2010
- document
-
Heijden, M.V.D. (author), Hinne, M. (author), Kraaij, W. (author), Verberney, S. (author), Weide, T.V.D. (author), TNO Informatie- en Communicatietechnologie (author)Logfles of search engines are a promising resource for data mining, since they provide raw data associated to users and web documents. In this paper we focus on the latter as- pect and explore how the information in logfles could be used to improve document descriptions. A pilot experiment demonstrated that document descriptors extracted from...conference paper 2009
- document
- Larson, M. (author), Ordelman, R. (author), de Jong, F. (author), Kraaij, W. (author), Kohler, J. (author), TNO Informatie- en Communicatietechnologie (author) conference paper 2009
- document
-
Hinne, M. (author), Kraaij, W. (author), Raaijmakers, S. (author), Verberne, S. (author), van der Weide, T. (author), van der Heijden, M. (author), TNO Informatie- en Communicatietechnologie (author)Recently a number of studies have demonstrated that search engine logfiles are an important resource to determine the relevance relation between URLs and query terms. We hypothesized that the queries associated with a URL could also be presented as useful URL metadata in a search engine result list, e.g. for helping to determine the semantic...conference paper 2009
- document
-
TNO Informatie- en Communicatietechnologie (author), Trieschnigg, D. (author), Pezik, P. (author), Lee, V. (author), Jong, F.de (author), Kraaij, W. (author), Rebholz-Schuhmann, D. (author)Motivation: Controlled vocabularies such as the Medical Subject Headings (MeSH) thesaurus and the Gene Ontology (GO) provide an efficient way of accessing and organizing biomedical information by reducing the ambiguity inherent to free-text data. Different methods of automating the assignment of MeSH concepts have been proposed to replace manual...article 2009
- document
- TNO Informatie- en Communicatietechnologie (author), Over, P. (author), Awad, G. (author), Buckland, L. (author), Dimmick, D. (author), Fiscus, J. (author), Michel, M. (author), Smeaton, A. (author), Kraaij, W. (author) conference paper 2009
- document
- TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author), Awad, G. (author), Over, P. (author) conference paper 2009
- document
- TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author), Awad, G. (author) conference paper 2009
- document
-
TNO Informatie- en communicatietechnologie (author), Verberne, S. (author), Hinne, M. (author), van der Heijden, M. (author), Kraaij, W. (author), D'hondt, E. (author), van der Weide, T. (author)A number of recent studies have investigated the relation be-ween URLs and associated query terms from search engine log files. In [5], the query terms associated with the domain of a URL were used as features for a URL classification task. The idea is that query terms that lead to successful classification of a URL are reliable semantic...conference paper 2009
- document
-
TNO Informatie- en communicatietechnologie (author), Doets, P.J. (author), Eendebak, P.T. (author), Ranguelova, E. (author), Kraaij, W. (author)TNO has evaluated a baseline audio and a video fingerprinting system based on robust hashing for the TRECVID 2008 copy detection task. We participated in the audio, the video and the combined audio-video copy detection task. The audio fingerprinting implementation clearly outperformed the video fingerprinting implementation. We combined the...conference paper 2009
- document
-
TNO Informatie- en communicatietechnologie (author), Raaijmakers, S. (author), Kraaij, W. (author)In this paper we describe the TNO approach to large-scale polarity classification of the Blog TREC 2008 dataset. Our participation consists of the submission of the 5 baseline runs provided by NIST, for which we applied a multinomial kernel machine operating on character n-gram representations.conference paper 2009
- document
- TNO Informatie- en communicatietechnologie (author), Over, P. (author), Awad, G. (author), Travis Rose, (author), Fiscus, J. (author), Kraaij, W. (author), Smeaton, A.F. (author) conference paper 2009
- document
-
Response to comment on 'MeSH-up: Effective MeSH text classification for improved document retrieval'TNO Informatie- en Communicatietechnologie (author), Trieschnigg, D. (author), Pezik, P. (author), Lee, V. (author), Jong, F.de (author), Kraaij, W. (author), Rebholz-Schuhmann, D. (author)As developers and primary users of MTI and MetaMap, Névéol et al. made a number of interesting comments on our recent publication in Bioinformatics. However, some of the results and conclusions found in the reply seem premature and lack proper clarification.article 2009
- document
-
TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author)Zoals eenieder zich nog wel de roes kan herinneren na de eindexamenuitslag van de middelbare school, zo heeft voor mij ook de eerste kennismaking met het world wide web een bijzondere indruk gemaakt. Het zal ergens in 1993 geweest zijn toen ik aan collega’s van het toenmalige Instituut voor Taal en Kennistechnologie van de Universiteit van...public lecture 2009
- document
-
Trieschnigg, D. (author), Meij, E. (author), de Rijke, M. (author), Kraaij, W. (author), TNO Informatie- en Communicatietechnologie (author)Over the years, the notion of concept relatedness has attracted considerable attention. A variety of approaches, based on ontology structure, information content, association, or context have been proposed to indicate the relatedness of abstract ideas. We propose a method based on the cross entropy reduction between language models of concepts...conference paper 2008
- document
-
Meij, E. (author), Trieschnigg, D. (author), de Rijke, M. (author), Kraaij, W. (author), TNO Informatie- en Communicatietechnologie (author)In many collections, documents are annotated using concepts from a structured knowledge source such as an ontology or thesaurus. Examples include the news domain [7], where each news item is categorized according to the nature of the event that took place, and Wikipedia, with its per-article categories [1]. These categorizing systems originally...conference paper 2008
- document
- TNO Informatie- en Communicatietechnologie (author), Over, P. (author), Awad, G. (author), Buckland, L. (author), Dimmick, D. (author), Fiscus, J. (author), Rose, T. (author), Michel, M. (author), Kraaij, W. (author), Smeaton, A.F. (author) conference paper 2008
- document
- TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author), Awad, G. (author), Over, P. (author) conference paper 2008
- document
- TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author), Awad, G. (author) conference paper 2008
- document
-
TNO Informatie- en Communicatietechnologie (author), Kraaij, W. (author), Raaijmakers, S.A. (author), Elzinga, P. (author)We propose a novel and intuitive way to quantify the utility of a classifier in cases where automatic classification is deployed as partial replacement of human effort, but accuracy requirements exceed the capabilities of the classifier at hand. in our approach, a binary classifier is combined with a meta-classifier mapping all decisions of the...conference paper 2008