We propose in this paper an approach to learn term to concept mapping with the joint utilization of an existing ontology and verb relations. This is a non-supervised solution that can be applied to any field for which an ontology modeling verbs as relations holding between the concepts was already created. Conceptual graphs are learned from a natural language corpus by using part-of-speech information and statistic measures. Labeling strategies are proposed to assign terms of the corpus to concepts of the ontology by taking into account the structure of the ontology and the extracted conceptual graphs. This paper presents the approach proposed to learn the conceptual graphs from the corpus and the labeling strategies. A first experimentation in the field of accidentology was done and its results are also presented.