01695nam a2200181 a 450000100080000000500110000800800410001902400350006010000220009524500720011726001690018930000140035852010450037265000260141765300340144365300130147770000230149010068762020-01-20       1998    bl uuuu     u00u1 u    #d7 a10.1109/SPIRE.1998.7129852DOI1 aNASCIMENTO, M. A.  aAn experiment stemming non-traditional text.h[electronic resource]  aIn: STRING PROCESSING AND INFORMATION RETRIEVAL: A SOUTH AMERICAN SYMPOSIUM, 1998, Santa Cruz de la Sierra. Proceedings... Los Alamitos: IEEE Computer Societyc1998  ap. 75-80.  aStemming is a technique which aims to extract common suffixes of words. Thus, words which are literally different but have a commom stem, may be abstracted by their common stem. The underlying goal when using a stemming techniques is to improve recall, at the possible expense of precision loss. A well known technique for stemming text is Porter's algorithm, which is based on a set of rules extracted from the English language. In this paper, we argue that such an algorithm it is not efficient for non-traditional texts, e.g., one made up mainly of medical terms. We thus investigate the use of a technique, called Peak-and-Plateau, which is based on tries, and compare it to Porter's algorithm. Our experiments have shown that using Porter's algorithm or none at all makes no difference as far as precision and recall goes. On the other hand, using the Peak-and Plateau technique we improved recall by about 15% and decreased precision by an average of 40%. Moreover, it compressed the original text by 40% and the inverted file by 45%.  aInformation retrieval  aRecuperação de informação  aStemming1 aCUNHA, A. C. R. da