Multi-document summarization by sentence extraction

Abstract

This paper discusses a text extraction approach to multidocument summarization that builds on single-document summarization methods by using additional, available in-, formation about the document set as a whole and the relationships between the documents. Multi-document summarization differs from single in that the issues of compression, speed, redundancy and passage selection are critical in the formation of useful summaries. Our approach addresses these issues by using domainindependent techniques based mainly on fast, statistical processing, a metric for reducing redundancy and maximizing diversity in the selected passages, and a modular framework to allow easy parameterization for different genres, corpora characteristics and user requirements.

Abstractive Multi-Document Summarization via Phrase Selection and Merging

“…Early studies mainly followed a greedy strategy in sentence selection (Ç elikyilmaz and Hakkani-Tür, 2011;Goldstein et al, 2000;Wan et al, 2007). Each sentence in the documents is firstly assigned a salience score.…”

Multidocument summarization via information extraction

“…The sentence extraction part of the RIPTIDES system is similar to the domain-independent multidocument summarizers of Goldstein et al [7] and Radev et al [11] in the way it clusters sentences across documents to help determine which sentences are central to the collection, as well as to reduce redundancy amongst sentences included in the summary. It is simpler than these systems insofar as it does not make use of comparisons to the centroid of the document set.…”

Redundancy and Collaboration in Wikibooks

“…Although this is challenging even with modern natural language processing techniques, a combination of techniques has proven to be effective, e.g. [9,20], and offers an approximation for the amount of similarity and thus redundancy between two sentences.…”