From Syntactical Analysis to Textual Segmentation

Abstract

In this work a proposal for automatic textual segmentation is described. The proposal uses the output of an automatic syntactic analyzer – Parser Palavras – to create textual segmentation. Parse trees are used to infer text segments and a dependency tree of the identified segments. The main contribution of this work is the use of the syntactic structure as source for the automatic segmentation of texts, as well, as the use of inference rules for the textual organization.