Document summarization is an important task in the area of natural language processing, which aims to extract the most important information from a single document or a cluster of documents. In various summarization tasks, the summary length is manually defined. However, how to find the proper summary length is quite a problem; and keeping all summaries restricted to the same length is not alwa...

The online information available on world wide web is in enormous amount. Search engines like Google, Yahoo were developed to retrieve information from the databases. But actual results were not obtained as the electronic information is increasing day by day. Thus automatic summarization came into demand. Automatic summarization gathers several documents as input and provides the shorter summar...

Speech-to-text summarization systems usually take as input the output of an automatic speech recognition (ASR) system that is affected by issues like speech recognition errors, disfluencies, or difficulties in the accurate identification of sentence boundaries. We propose the inclusion of related, solid background information to cope with the difficulties of summarizing spoken language and the ...

1 Description of the system ModDBS-X is a clustering based single document summarizer. It is an open-domain extractive summarizer, demanding of the input nothing more than the availability of basic IR statistics such as term and document frequency. Therefore it could be adapted for any language and domain without much effort. The system goes through three major states to generate a summary: dat...

We present a supervised sentence ranking approach for use in extractive summarization. Using a general machine learning technique provides great flexibility for incorporating varied new features, which we demonstrate. The system proves quite effective at query-focused multi-document summarization, both for single summaries and for series of update summaries.

Extractive multi-document summarization is mostly treated as a sentence ranking problem. Existing graph-based ranking methods for key-sentence extraction usually attempt to compute a global importance score for each sentence under a single relation. Motivated by the fact that both documents and sentences can be presented by a mixture of semantic topics detected by Latent Dirichlet Allocation (L...

This paper presents an approach to summarize single scientific papers, by extracting its contributions from the set of citation sentences written in other papers. Our methodology is based on extracting significant keyphrases from the set of citation sentences and using these keyphrases to build the summary. Comparisons show how this methodology excels at the task of single paper summarization, ...

Recent studies on extractive text summarization formulate it as a combinatorial optimization problem such as a Knapsack Problem, a Maximum Coverage Problem or a Budgeted Median Problem. These methods successfully improved summarization quality, but they did not consider the rhetorical relations between the textual units of a source document. Thus, summaries generated by these methods may lack l...

Multi-document summarization is the automatic production of a unique summary from a collection of texts. In this paper, we propose a statistical generative approach for multi-document summarization that combines simple information such as sentence position in the text and semantic-discursive information from CST (Cross-Document Structure Theory). In particular, we formulate the multi-document s...

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...