Extraction and representation of contextual information for knowledge discovery in texts Patrick Perrin a, * ,1 , Frederick E. Petry b, * a Merck Research Laboratories, Medicinal Chemistry/Molecular Systems, Rahway, NJ 07065, USA b Department of Electrical Engineering and Computer Science, Tulane University, New Orleans, LA 70118, USA Received 8 October 2000; received in revised form 19 May 2002; accepted 24 June 2002 Abstract This paper studies the role of lexical contextual relations for the problem of unsu- pervised knowledge discovery in full texts. Narrative texts have inherent structure dic- tated by language usage in generating them. We suggest that the relative distance of terms within a text gives sufficient information about its structure and its relevant content. Furthermore, this structure can be used to discover implicit knowledge em- beddedinthetext,thereforeservingasagoodcandidatetorepresenteffectivelythetext content for knowledge elicitation tasks. We qualitatively demonstrate that a useful text structure and content can be systematically extracted by collocational lexical analysis without the need to encode any supplemental sources of knowledge. We present an algorithmthatsystematicallyextractsthemostrelevantfactsinthetextsandlabelsthem by their overall theme, dictated by local contextual information. It exploits domain independent lexical frequencies and mutual information measures to find the relevant contextualunitsinthetexts.Wereportresultsfromexperimentsinareal-worldtextual database of psychiatric evaluation reports. Ó 2002 Elsevier Science Inc. All rights reserved. Information Sciences 151 (2003) 125–152 www.elsevier.com/locate/ins * Corresponding authors. E-mail addresses: patrick_perrin@merck.com (P. Perrin), fep@eecs.tulane.edu, petry@eecs. tulane.edu (F.E. Petry). 1 At the time of this research, this author was at Tulane University, Department of Computer Science, New Orleans, LA 70118, USA. 0020-0255/02/$ - see front matter Ó 2002 Elsevier Science Inc. All rights reserved. doi:10.1016/S0020-0255(02)00400-0