摘要：Effective information retrieval requires an efficient indexing technique. With the availability of huge volume of information, it has become necessary to capture the semantic of the document, which is almost impossible with the existing techniques. Moreover in the existing technique the weights once assign are remains unchangeable through out the cycle. In this paper an indexing technique assignment using Rhetorical Structure Theory with dynamic weight assignment technique has been presented. The nodes of Rhetorical Parsing tree contain relations and text spans which can be used for indexing by indexer. The results are promising for different texts. Enhancing the technique of NLP can improve the proposed algorithm to accommodate more relations and huge documents.
