An approach to graph-based analysis of textual documents
Antoon Bronselaer, Gabriella Pasi · 2013
In this paper a new graph-based model is proposed for the representation of textual documents.Graph-structures are obtained from textual documents by making use of the well-known Part-Of-Speech (POS) tagging technique.More specifically, a simple rule-based (re)classifier is used to map each tag onto graph vertices and edges.As a result, a decomposition of textual documents is obtained where tokens are automatically parsed and attached to either a vertex or an edge.It is shown how textual documents can be aggregated through their graph-structures and finally, it is shown how vertex-ranking methods can be used to find relevant tokens. 1 .