In tune with the recent developments in the automatic retrieval of text semantics, this paper is an attempt to extract one of the most fundamental semantic units from natural language text. The context is intuitively extracted from typed dependency structures basically depicting dependency relations instead of Part-Of-Speech tagged representation of the text. The dependency relations imply deep, fine grained, labeled dependencies that encode longdistance relations and passive information. Apart from the typed dependencies, the present work does not take the help of Noun phrase Chunking tool or Part of speech Taggers for the compound noun phrase extraction.
展开▼
