Automatic Multilingual Indexing and Natural Language Processing

The number of documents being collected by information brokers such as bibliographic database producers, libraries and publishers increases rapidly. The consequence is a huge demand for indexing and classification. So far this has had to be carried out manually. The system AUTINDEX, which is described in this paper offers tools for monolingual as well as for multilingual automatic indexing and classification by taking advantage of sophisticated language processing technologies and already existing special purpose language resources such as thesauri, classification schemes and large lexicons. It will be shown that the use of high quality NLP can achieve appropriate results.