Now a days there is great amount of information available due to the development of Internet technologies. Every time when someone searches something on the Internet, the response obtained is a huge one with lots of information, which is impossible for a person to read completely. Hence one needs means of producing summaries of this information. Summarization is a very interesting and useful task which gives support to many other tasks like information extraction. It takes advantage of the techniques developed for Natural Language Processing tasks. In automatic text summarization most of the times the standard N gram model is used to develop the language model. The N gram models are unable to learn the grammatical relations of the sentences. Hence we propose to use the dependency grammar based noun phrase retrieval as a part of text preprocessing. This can be useful to learn the grammatical rules and thereby may be helpful to extract fundamental semantic units from the natural language text.
展开▼
