The travel and tourism sector is one of the biggest economic branches world-wide. Also for this sector the Internet and in particular the World Wide Web plays an increasingly important role, be it for the purpose of providing information or in the form of actual commercial transactions. More and more users gather relevant information through the internet and take to planning and organising their journeys through the electronic media. It is almost an inherent feature of the sector, that the information has to be offered and is sought for in different languages. However, multilinguality is at the same time one of the biggest barriers for an efficient and user-friendly search and presentation of the information.
The project mietta will develop a system which will allow the user to search in his own language for tourist information on the web and which at the same time supports the information provider to offer this information in different languages. mietta will develop and integrate a broad range of technologies for the capturing of information, for search and for presentation of information, which can consist of various types of data ranging from free text via semi-structured information to pure database entries. The user will be able to retrieve the information in his language either as automatically translated documents or as text generated automatically from information that has been extracted and condensed from the original documents. The languages covered will be English, Finnish, French, German and Italian.
- Flexible cross-lingual access to tourist information in the web
- Advanced indexing and retrieval methods through the combination of language technology and statistical methods
- Structured analysis and presentation of unstructured information through information extraction technology
- Presentation of information in different languages through machine translation and multi-lingual generation