Towards Logical Representation of Language Structure

This article is meant as a basis for a semantic annotation manual. The annotation will translate the logical structure of written and spoken speech by a language-independent manner. The basis for this thesis can be found in temporal logic of Mark Steedman and the formalism introduced here elaborates on Patrick Blackburn’s hybrid multimodal logic and Dependency Grammar Logic of Geert-Jan Kruijff, although it represents not the level of linguistic meaning but rather the level of logical meaning (content). The main issues discussed in this article are input text segmentation into logical units, discourse referents representation, time-spatial representation, the impact of topic-focus articulation on the logical content and the semantic categories needed for the annotation. In the last two sections a complete discourse example and the annotation of 37 test cases of Jan Hajič are presented.