MIETTA - A framework for uniform and multilingual access to structured database and web information

Abstract

We describe a WWW-based information system called MIETTA, which allows uniform and multilingual access to heterogenous data sources in the tourism domain. The design of the search engine is based on a new crosslingual framework. The framework integrates a crosslingual retrieval strategy with a strategy using natural language techniques: information extraction and multilingual generation. The combination of information extraction and multilingual generation enables on the one hand, multilingual presentation of the database content, and on the other hand, free text crosslingual information retrieval of the structured data entries. We will demonstrate that the new framework is useful for domain specific and multilingual applications.