Abstract - Text summarization is an important problem, which has numerous applications. This problem has been extensively studied and many approaches have been proposed in the literature for its solution. In this paper, we investigate a new approach that employs meta-search. In particular, summaries from several summarizers are evaluated and a new summary is formed from these summaries. Clearly, this meta-summarizer will produce a better summary than any of the others since it exploits the special features of all the sources. We have employed data from Document Understanding Conference 2002 (DUC-2002) and 5 different summarizers in our experiments. We have also created our own summarizer.

Summarization evaluation has been always a challenge to researchers in the document summarization field. Usually, human involvement is necessary to evaluate the quality of a summary. Here we present a new method for automatic evaluation of text summaries by using document graphs. Data from Document Understanding Conference 2002 (DUC- 2002) has been used in the experiment. We propose measuring the similarity between two summaries or between a summary and a document based on the concepts/entities and relations between them in the text.

Text summarization is an important problem since it has numerous applications. This problem has been extensively studied and many approaches have been pro-posed in the literature for its solution. One such interesting approach is that of posing summarization as an optimization problem and using genetic algorithms to solve this optimization problem. In this paper we present elegant randomized algorithms for summarization based on sampling. Our experimental results show that our algorithms yield nearly the same accuracy as the genetic algorithms while significantly saving on time. We have employed data from Document Understanding Conference 2002 and 2004 (DUC-2002, DUC-2004) in our experiments

Text summarization is an important problem,which has numerous applications. This problem has been extensively studied and many approaches have been proposed in the literature for its solution. One of the most challenging problems in the field of text summarization is generating a user-focused summary based on a query. In this paper, we investigate a new approach that tackles this problem and propose a new solution using document graphs. This is our first time to participate in Document Understanding Conferences.

Text summarization is an important problem, which has numerous applications. This problem has been extensively studied and many approaches have been proposed in the literature for its solution. One of the most challenging problems in the field of text summarization is generating a user-focused summary based on a query. In this paper, we investigate a new approach that tackles this problem and proposes a new solution using document graphs. We have employed data from Document Understanding Conference 2006 (DUC-2006).