This paper presents a novel algorithm for the acquisition of Information Extraction patterns. The approach makes the assumption that useful patterns will have similar meanings to those already identified as relevant. Patterns are compared using a variation of the standard vector space model in which information from an ontology is used to capture semantic similarity. Evaluation shows this algor...

SUMMARY IE-Kb (Intron Exon-Knowledge base) illustrates the intron-exon dynamics in eukaryotic genes. We have developed three different knowledge sets, namely 'Non-redundant ExInt', 'Non-redundant Pfam-ExInt complement' and 'Non-redundant GenBank eukaryotic subdivisional sets' to understand this phenomenon. Statistical analysis is performed on each knowledge set and the results are made availabl...

dans cet article, l'auteur tudie la creation d'une voie ferre interurbaine, de la banlieue ou urbaine, et essaie de d6terminer le nombre optimal de stations pour une longueur donnee de la ligne; compte tenue d'une repartion du trafic, ie long de la ligne en question qui est suppose etre connue. le critere d'optimalisation est le temps total perdu par l'ensemble des usag...

dans cet article i' intervalle entre deux trains successifs a ete etudie en fonction de leur vitesses dans deux cas differents. dans ie premier cas ,on suppose que la vitesse des deux trains a une valeur constante, et on etudie les variations de l'intervalle minimum en fonction de la vitesse on determine la vitesse optimale et on etudie les variations de l'intervalle minimum en f...

For the update summaries task of the Text Analysis Conference 2008 we have implemented a novel summarization technique based on query expansion with encyclopedic knowledge and activation spreading in a large document graph. We have also experimented with sentence compression for building the summaries. The results are average – ranked 27 out of 58 for responsiveness in manual evaluation – but w...

We propose a framework for deterministic simulation of user behavior that allows to analyze the cost-gain-based performance on single result lists or whole search sessions. The ideal user representing optimal behavior (i.e., most gain with lowest effort) is contrasted with more “average” users that employ the spreading activation model from cognitive theory. On TREC Session Track data, the idea...