A Survey of Generating Multi-Document Summarizations

Patil Ajita S., P. M. Mane

Abstract: Summarization is a Process of filtering the most important information from a source/sources for a particular user and task. Summarization is a very useful task which gives support to many other tasks. It takes advantage of the techniques developed for Natural Language Processing tasks. Multidocument summarization is a technique of summarize the multiple document into one paragraph. Multi-document summarization is different from single-document summarization. Single-document summarization can be considered as one of the sub-tasks of multi-document summarization. There exist several other important sub-tasks including identification of important common ideas in the documents, selecting representative summaries for each of these ideas and organizing the indicative summaries for the final summary. In this paper we describe a system for multi-document summarization. This survey plan to analyze some of the most relevant approaches in the areas of multiple-document summarization, giving special importance to empirical methods and extractive techniques.

Keywords: Multi-document summarization, Text Summarization, Text mining, Information Extraction