|
Abstract : |
busemanndfk, uni-sb, de Appointment scheduling is a problem faced daily by many individuals and organiza-tions. Cooperating agent systems have been developed to partially automate this task. In order to extend the circle of par-ticipants as far as possible we advocate the use of natural language transmitted by e-mail. We describe COSMA, a fully imple-mented German language server for exist-ing appointment scheduling agent systems. COSMA can cope with multiple dialogues in parallel, and accounts for differences in di-alogue behaviour between human and ma-chine agents. NL coverage of the sub-language is achieved through both corpus-based grammar development and the use of message extraction techniques. 1, |
