The paper presents two useful extensions of the incremental SVM in the context of online learning. An online support vector data description algorithm enables application of the online paradigm to unsupervised learning. Furthermore, online learning can be used in the large-scale classification problems to limit the memory requirements for storage of the kernel matrix. The proposed algorithms ar...

This report briefly summarizes the discussions carried out in the working group on classification, representation and modeling of uncertain data. The discussion was divided into two subgroups: the first subgroup studied how different representation and modeling alternatives currently proposed can fit in a bigger picture of theory and technology interaction, while the second subgroup focused on ...

This paper describes our participation in the MWE 2008 evaluation campaign focused on ranking MWE candidates. Our ranking system employed 55 association measures combined by standard statistical-classification methods modified to provide scores for ranking. Our results were crossvalidated and compared by Mean Average Precision. In most of the experiments we observed significant performance impr...

In this paper, we present an efficient semiautomatic method for annotating English phrasal verbs on the OntoNotes corpus. Our method first constructs a phrasal verb dictionary based on Wiktionary, then annotates each candidate example on the corpus as an either a phrasal verb usage or a literal one. For efficient annotation, we use the dependency structure of a sentence to filter out highly pla...

We address the problem of classifying multiword expression tokens in running text. We focus our study on Verb-Noun Constructions (VNC) that vary in their idiomaticity depending on context. VNC tokens are classified as either idiomatic or literal. Our approach hinges upon the assumption that a literal VNC will have more in common with its component words than an idiomatic one. Commonality is mea...

This paper introduces two approaches to develop the network protocol analyzers, one of which is based on NDIS (Network Driver Interface Specification), the other is based on WinPcap. The second approach is discussed in details. This paper outlines the WinPcap architecture. Functions exported by WinPcap are classified in three types. On this classification, we can accurately configure the develo...

This document reports the final, detailed result of the study on current and future technologies for collaborative working environments (CWEs). The goal of this study is to analyze current CWEs and whether they and their future trends are suitable for largescale multinational organizations. To this end, we have analyzed the structure of large-scale organizations in general, and of ESA in partic...