A domain specific lexicon acquisition tool for cross-language information retrieval

Abstract

With the recent enormous increase of information dissemination via the web as incentive there is a growing interest in supporting tools for cross-language retrieval. In this paper we describe a disclosure and retrieval approach that fulfills the needs of both information providers and users by o ering fast and cheap access to a large amounts of documents from various language domains. Relevant information can be retrieved irrespective of the language used for the specification of a query. In order to realize this type of multilingual functionality theavailability of several translation tools is needed, both of a generic and a domain specific nature. Domain specific tools are often not available or only against large costs. In this paper we will therefore focus on a way to reduce these costs, namely the automatic derivation of multilingual resources from so-called parallel text corpora. The bene ts of this approach will be illustrated for an example system, i.e. the demonstrator developed within the project Twenty-One, which is tuned to information from the area of sustainable development.