A Rule-based Semantic Frame Annotation of Arabic Speech Turns for Automatic Dialogue Analysis

In this article, and after sketching the state of the art on semantic representations, we have deduced that an important technological lock that hinders the H/M Spoken Dialogue System (SDS) is the adoption of the attribute/value schemes as a semantic representation. Besides, current systems, using such a representation (form of a formula), constrain too much their users to behave according to the model set by the designer. Thus, in order to overcome all the limitations of the modeling by a pre-established form, we decided to choose the use of semantic frames as a representation of the meanings of Arabic user statements. In this perspective, the choice of the FrameNet paradigm as a high level semantic representation seems appropriate. In addition to the robustness of the paradigm, FrameNet has the advantage of producing standard annotations that are easy to share and compare within the scientific community. To represent more complex user rounds, we propose to use, in the understanding module, a semantic model that is more flexible than that of a predefined form.