Centroid-based summarization of multiple documents
We propose an efficient text summarization technique that involves two basic operations. The first operation involves finding coherent chunks in the document and the second operation involves ranking the text in the individual coherent chunks and picking the sentences that rank above a given threshold. The coherent chunks are formed by exploiting the lexical relationship between adjacent sentences in the document. Occurrence of words through repetition or relatedness by sense relation plays a major role in forming a cohesive tie. The proposed text ranking approach is based on a graph theoretic ranking model applied to text summarization task.