Automatic Processing of Written French Language

AUTOMATIC PROCESSING OF WRITTEN FRENCH LANGUAGE J.L.Binot, M.Graitson, Ph. Lemaire, D.Ribbens Computer Sciences Department University of Liege Belgium Abstract An automatic processor of written French language is described. This processor uses syntactic and semantic informations about words in order to construct a se- mantic net representing the meaning of the sentences. The structure of the net- work and the principles of the parser are explained. An application to the pro- cessing of the medical records is then discussed. I. Introduction SABA ("Semantic Analyser , Backward Ap- proach") is an automatic parser of French language currently developped at Liege University, Belgium I. It is now aimed at the processing of medical records 2. Howe- ver, the principles of this system were conceived independently of any specific application. SABA has been fundamentally conceived as a general, flexible French language parser, which could be used as a component of a natural language inter- face between a human user and a given computer process 8. This parser is not li- mited to the processing of correct, aca- demic French. It is aimed also at pro- cessing the casual language of an ave- rage user. Though our system is uniquely concerned with French, we have translated our examples in English everytime that it was possible. In this way, we hope that the non French-speaking reader might be able to get the flavour of our work. 2. General description of the s~stem SABA, as a parsing system, is essentially semantically oriented, Its goal is not to identify the complete syntactic struc- ture of the input sentences, but rather to determine the possible semantic re- lationships between the terms of these sentences. More specifically, the system tries to characterize the semantic depen- dencies that appear in a sentence bet- ween the complements and the terms which are completed by them (from now on, a term of this last kind will be called a "completee"). We will insist immediately upon the fact that both concepts of"com- plement" and of "completee" are to be taken in a general way. The syntactic subject of a verb is thus treated as a complement of this verb. To characterize these semantic dependen- cies, the system uses a small set of re- lationships like AGENT, OBJECT, INSTRU- MENT, LOCUS, and so on. In this way, our system is related to the family of "case systems", using the now well known prin- ciples of case grammars 3 14 However, in contrast to some authors 3 15 17 18 , we don~t try to find a complete and minimal set of universal relationships. The only criterion for the choice of our relation- ships is their practical usefulness. For the time being, about twenty different relationships are used by the system. All the relationships which are identified in an input sentence are summarized in a semantic network, which represents the semantic structure of this sentence. The (simplified) representation of a complete sentence may be illustrated by the figu- re I. The fundamental principles of the network …

Content truncated to 500 words