We have performed a set of experiments made to investigate the utility of morphological analysis to improve retrieval of documents written in languages with relatively large morphological variation in a practical commercial setting, using the SiteSeeker search system developed and marketed by Euroling AB. The objective of the experiments was to evaluate different lemmatisers and stemmers to det...

Lyytikäinen, Virpi Contextual and structural metadata in enterprise document management Documents have a central role in organizations. While the amount of information continually increases, new kinds of methods for managing the documents are needed. Enterprise document management concerns the whole life cycle of documents in organizations, from emergence to disposition, and also development of...

This work deals with the reconstruction of hand-torn documents from pairs of aligned fragments. In the first step we use a recent approach to estimate hypotheses for aligning pieces from a set of magazine pages. We then train a structural support vector machine to determine the compatibility of previously aligned pieces along their adjacent contour regions. Based on the output of this discrimin...

Daily activities carried out with paper documents are nowadays transposed onto their digital counterparts. A plethora of software enable people to achieve document-related activities. In particular, these comprise information retrieval used while drafting new documents. Documents may later be disseminated, exploited and organized in readers’ document repositories. Our study on current systems s...

We propose a new method for Information Retrieval (IR) based on graph vertices comparison. The main goal of this method is to enhance the core IR-process of finding relevant documents in a collection of documents according to a user’s needs. The method we propose is based on graph comparison and involves recursive computation of similarity. In the framework this approach, documents, queries and...

Text classification is a natural application domain for semisupervised learning, as labeling documents is expensive, but on the other hand usually an abundance of unlabeled documents is available. We describe a novel simple twostage scheme based on dagging which allows for utilizing the test set in model selection. The dagging ensemble can also be used by itself instead of the original classifi...

Preliminary works have already been performed between IRCCyN, IRAP and CNES. In particular, the paper [1] proposes a blind estimation method under the assumption of a purely linear response. A possible direction of the proposed project could be to generalize the latter method. On the one hand, an affine model would be more realistic. On the other hand, a totally unsupervised method would be pre...

Recent advances in the study of spontaneous brain activity have demonstrated activity patterns that emerge with no task performance or sensory stimulation; these discoveries hold promise for the study of higher-order associative network functionality. Additionally, such advances are argued to be relevant in pathological states, such as disorders of consciousness (DOC), i.e., coma, vegetative an...

Quick and efficient processing of images is an important request of various disciplines and several applied fields. Many authors have studied specialized computing architectures (with electronic technology) devoted to image processing (see, for example, Refs. 1-5), but other authors have pointed out that optical computing architectures are more suitable for massive computation on images because...