Homepage > Papers

            

                Methods for reports processing which reveal the

                    characteristics of figurants and incidents

              

          Igor P. Kuznetsov, (Moscow, Institute for Informatics Problems of the Russian Academy of Sciences)

 

                                      RESUME

 

     A class of systems is considered designed for processing of reports for the tasks of Criminal Investigation   Departments. The design is based on the fact that the reports are natural language texts abounding in abbreviations and synonymous ways of expressing the same content.  This kind of system should be provided with the features of  analysis  for  ambiguity  elimination  at   different levels, for  restoration of insufficient information and supplying it with relevant characteristics,  for supporting the  variety  of terms in the course of similar incidents and figurants retrieval.

     This paper describes an approach to the development  of  such systems   which  consists  in  employing  a  linguistic  processor providing lexical  and  morphological  analyses  followed  by  the subsequent simplest   semantic   network  formation.  The further processing is completely transformed to the level of such networks and is   performed on the basis of logical-analytical means and methods. The use of this type of networks for   representation of content images of  documents and for a terminological dictionary presentation are considered as well as their use for revealing the incidents and figurant characteristics and for the retrieval space expansion.