Abstract
The needs for managing similar documents in different languages increases with the growing amounts of electronic information available in documents of the same type (e.g. news streams). This paper proposes a viable approach to information access emphasizing the hypertextual paradigm in a multilingual framework. This task of processing/structuring text so that cross-lingual hypertext links are generated will be called Multilingual Authoring (MA). Methods from Natural Language Processing, especially Information Extraction, to both monolingual and Multilingual Authoring will be described and a general architecture for MAw ll be defined. Effectiveness of the proposed approach will be discussed the description of the NAMIC prototype system 1