Abstract

Complex documents stored in a at or partially marked up le format require layout sensitive preprocessing before any natural language processing can be carried out on their textual content. Contemporary technology for the discovery of basic textual units is based on either spatial or other content insensitive methods. However, there are many cases where knowledge of both the language and layout is required in order to establish the boundaries of the basic textual blocks. This paper describes a number of these cases and proposes the application of a general method combining knowledge about language with knowledge about the spatial arrangement of text. We claim that the comprehensive understanding of layout can only be achieved through the exploitation of layout knowledge and language knowledge in an inter-dependent manner. 1 Introduction There is currently a signicant amount of work being carried out on applications which aim to deduce layout information from a spatial description o...

Citations