Knowledge Discovery in Literature Data Bases

The concept of knowledge discovery as defined through “establishing previously unknown and unsuspected relations of features in a data base” is, cum grano salis, relatively easy to implement for data bases containing numerical data. Increasingly we find at our disposal data bases containing scientific literature. Computer assisted detection of unknown relations of features in such data bases would be extremely valuable and would lead to new scientific insights. However, the current representation of scientific knowledge in such data bases is not conducive to computer processing. Any correlation of features still has to be done by the human reader, a process which is plagued by ineffectiveness and incompleteness. On the other hand we note that considerable progress is being made in an area where reading all available material is totally prohibitive: the World Wide Web. Robots and Web crawlers mine the Web continuously and construct data bases which allow the identification of pages of interest in near real time. An obvious step is to categorize and classify the documents in the text data base. This can be used to identify papers worth reading, or which are of unexpected cross-relevance. We show the results of first experiments using unsupervised classification based on neural networks. 1. The Astronomical Research Process The research process has only recently been defined in epistemological terms: the model developed by Sir Karl Popper (1972) comes closest to what most natural scientists do when they “do science”. Briefly, the research process starts with the input of signals, either through sensory perception, or through measuring devices which register signals which Astrophysics Division, Space Science Department, European Space Agency