We present a multi-document summarizer, called MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We also describe two new techniques, based on sentence utility and subsumption, which we have applied to the evaluation of both single and multiple document summaries. Finally, we describe two user studies that test our models of multi-documen...

The goal of automated summarization is to tackle the “information overload” problem by extracting and perhaps compressing the most important content of a document. Due to the difficulty that singledocument summarization has in beating a standard baseline, especially for news articles, most efforts are currently focused on multi-document summarization. The goal of this study is to reconsider the...

A summary is a shorter version of the original. Such a simplification highlights the major points from the much longer subject, such as a text, speech, film, or event. The purpose is to help the audience get the gist in a short period of time. Automatic summarization involves reducing a text document or a larger corpus of multiple documents into a short set of words or paragraph that conveys th...

Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization...

We introduce the novel problem of automatic related work summarization. Given multiple articles (e.g., conference/journal papers) as input, a related work summarization system creates a topic-biased summary of related work specific to the target paper. Our prototype Related Work Summarization system, ReWoS, takes in set of keywords arranged in a hierarchical fashion that describes a target pape...

Summarization systems and Question Answering systems can be treated to have complementary functionality to each other. For instance, a question answering system could have a summarization module, that can summarize the fragments of answers found by the question answering system. On the other hand a summarization system can be given a question as input, to generate a question focused summary as ...

In this paper, we propose a summarization system which automatically classifies type of document set and summarizes a document set with its appropriate summarization mechanism. This system will classify a document set into three types: (a) One topic type, (b) multi-topic type, and (c) others. These types will be identified using information of high frequency nouns and Named Entity. In our multi...

The increasing amount of online content motivated the development of multi-document summarization methods. In this work, we explore straightforward approaches to extend single-document summarization methods to multi-document summarization. The proposed methods are based on the hierarchical combination of single-document summaries, and achieves state of the art results.

coherency—and be able to draw the “best” information from a set of documents. Automatic single-document text summarization1 has been an active research area since the 1950s, with a renaissance of approaches since the 1990s. Human single-document summarization is well defined when guidelines and recommendations drive performance.2,3 System-generated single-document summaries, while not always ma...