The study is a part of the author's PhD thesis. The thesis seeks solutions for quality based information retrieval, based upon text analysis, stating that quality content analysis must start from the linguistic analysis of the text. The technological developments of the last decades show that only some aspects of the quality information provision can be solved by automation. Modern computer technology can handle vast amount of information very fast and correctly. But the larger the amount of information is the more difficult is to design search engines which promote quality based selection. Artificial intelligence cannot solve all the problems of quality text analysis, but can be a good help in order to focus our resources on intellectual problems instead of mechanic tasks. The study shows some very promising research projects representing the very new approaches of text-based information retrieval. The projects mainly are parts of the American TREC program.
Financed by the National Centre for Research and Development under grant No. SP/I/1/77065/10 by the strategic scientific research and experimental development program:
SYNAT - “Interdisciplinary System for Interactive Scientific and Scientific-Technical Information”.