French pharmaceutical thesis are seldom refered to. If the main obstacles originate from language or access barriers, proper indexation could also be blaimed. Manually extracted key words dont necessary come from a structured thesaurus. In the following work, this manual indexing method is compared to an automated one, No-mindex, based on UMLS. The automated method is further improved by the addition of a relevance scoring system. The first step consists in downloading, adapting and indexing

more »

... sis in electronic format. Results will then be analysed, sorted by relevance, by comparing classic statistical indices (noise/silence/relevance). It was assumed that the manually obtained key words were always relevant. The manual silence is nevertheless high : 7 new key word are proposed by Nomindex, which results are mixed (10 Theses results are promising for a the first experience an pharmaceutical document without dictionary improvement : the indexing, if it is currently insufficient for a direct use, could easily be improve by specific updates of the dictionary