The volume of electronic text in different languages, particularly on the World Wide Web, is growing significantly, and the problem of users who are restricted in the number of languages they read obtaining information from this text is becoming more widespread. This paper investigates some of the issues involved in achieving multilingual Information Extraction (IE), describes the approach adopted in the M-LaSIE-II IE system which addresses these problems, and presents the results of evaluating the approach against a small parallel corpus of English/French newswire texts. The approach is based on the assumption that it is possible to construct a language independent representation of concepts relevant to the domain, at least for the small well-defined domains typical of IE tasks, allowing multilingual IE to be successfully carried out without requiring full Machine Translation.

Recent years have seen a dramatic increase in the development of agent technology. Agent systems have been applied to many areas, but undoubtedly the most widely publicised application area has been the Internet. The size of the Internet and the subsequent large volume of information has spawned agents which can search, filter, recommend and present information to a user. Many such agent applications can be customised to the preferences of the user. Indeed, most go further in including a profile of the user which is used to guide the operation of the agent. But what is a user profile? The purpose of this paper is to review the personalisation of agent technology, and to consider what implications arise for future personal agent applications. Following the review of a number of existing agent applications with user profiling abilities, we discuss the Open Profiling Standard as the first attempt to describe the content and widespread use of user profile information. We then identify four...

We present in this paper the coreference mechanism implemented in the M-LaSIE system, a prototype multilingual Information Extraction (IE) system. We describe an experiment in which texts from a parallel French/English corpus were marked up manually and processed by the system following the MUC coreference annotation scheme. This experiment allows us to assess the applicability of the MUC annotation scheme to a non-English language, to make several observations about differences in coreference behaviour in English and French, and to assess in a tentative way the cross-language portability of the M-LaSIE approach to coreference resolution.

In this paper we describe our approach to Text Mining by introducing TextMiner. We perform term and event extraction on each document to find features that are likely to have meaning in the domain, and then apply mining on the extracted features labelling each document. The system consists of two major components, the Text Analysis component and the Data Mining component. The Text Analysis component converts semi structured data such as documents into structured data stored in a database. The second component applies data mining techniques on the output of the first component. We apply our approach in the financial domain (financial documents collection) and our main targets are: a) To manage all the available information, for example classify documents in appropriate categories and b) To "mine" the data in order to "discover" useful knowledge. This work is designed to primarily support two languages, i.e. English and Greek. 1.

This paper reports work on automated meta-data creation for multimedia content. The approach results in the generation of a conceptual index of the content which may then be searched via semantic categories instead of keywords. The novelty of the work is to exploit multiple sources of information relating to video content (in this case the rich range of sources covering important sports events). News, commentaries and web reports covering international football games in multiple languages and multiple modalities is analysed and the resultant data merged. This merging process leads to increased accuracy relative to individual sources. 1

Traditional media have concepts to ensure quality of information they carry, while new media make information ubiquitious. The NetAcademy project constitutes a new medium for knowledge accumulation and dissemination for scienti#c purposes. It provides by its underlying carrier, the Internet, access to information and by its management concepts quality of information. We explore the NetAcademy with its open, distributed architecture, the NetAcademyNet and discuss, how such a medium as the NetAcademy will in#uence the process of publishing and scienti#c work. Keywords: Online publishing, Knowledge Management, Multi-agent system. 1

This paper presents the exibum system : a bilingual information extraction system currently being developed at the University of Montreal. exibum is an experimental system for analyzing French and English terrorist events from newswires and producing a template of the most pertinent information. exibum consists of the following modules : a language identifier, a part-of-speech tagger, a transcriber, a filter, a syntactic analyzer, a semantic analyzer, a discourse analyser, and a formatter. An interesting characteristic of exibum is that many of its components are o#-the-shelf systems not initially intended for information extraction. The rapid results obtained through this experiment demonstrate the great advantage of system re-use in this domain, and leave us optimistic for the future development of multilingual information extraction systems. 1 Introduction L'extraction d'information consiste a extraire de l'information precise du contenu d'un document et a la representer sous form...

this article we were largely successful with all slots except for the Entity Descriptor slot where scores were 50 % precision and 21 % recall. We will first explain the particular items we failed on, and then discuss why our Entity Descriptor slots were so poor

Abstract not found

Traditional media have concepts to ensure quality of information they carry, while new media make information ubiquitious. The NetAcademy project constitutes a new medium for knowledge accumulation and dissemination for scienti#c purposes. It provides by its underlying carrier, the Internet, access to information and by its management concepts quality of information. We explore