An ontology-based information extraction and summarization of multiple news articles

Abstract

Ontology based information extraction and summarization process in news content retrieved the news based on the user query. The user query should be of any context about the news content. So that, users need not be aware of the information that they search. This type of ontology based multi-document summarization system mainly focused on abstract document found in the news content. So, we proposed a work to combine information extraction, Abstraction based summarization and natural language generation to generate efficient multi-document summarization from multiple news articles. In this paper, we proposed an IE-supported summarization system that automatically extracts keyword for text summarization in Tamil e-newspaper datasets. The system first requires that the user need to select the particular domain. A set of news articles related to the domain is searched by search engine. One or more scenario templates (likes extraction domains such as Science, and technology, sports and natural disasters) are used to activate the system. The user optionally provides filters and preferences on the scenario template slots, specifying what information he/she wants to be reported in the summary. Then the system invokes the Summarizer to generate a natural language summary of the extracted information subject to the user’s constraints.