scispace - formally typeset
Search or ask a question
Topic

Multi-document summarization

About: Multi-document summarization is a research topic. Over the lifetime, 2270 publications have been published within this topic receiving 71850 citations.


Papers
More filters
Proceedings Article
01 Jan 2016
TL;DR: A submodular function-based summarization system which integrates three important measures namely importance, coverage, and non-redundancy to detect the important sentences for the summary is proposed.
Abstract: We propose a submodular function-based summarization system which integrates three important measures namely importance, coverage, and non-redundancy to detect the important sentences for the summary. We design monotone and submodular functions which allow us to apply an efficient and scalable greedy algorithm to obtain informative and well-covered summaries. In addition, we integrate two abstraction-based methods namely sentence compression and merging for generating an abstractive sentence set. We design our summarization models for both generic and query-focused summarization. Experimental results on DUC-2004 and DUC-2007 datasets show that our generic and query-focused summarizers have outperformed the state-of-the-art summarization systems in terms of ROUGE-1 and ROUGE-2 recall and F-measure.

22 citations

Proceedings ArticleDOI
29 May 2012
TL;DR: A document summarization method based on heterogeneous graph which is first implemented by constructing a graph which reflect relationship between different size of granularity nodes, and then using ranking algorithm to calculate score of nodes.
Abstract: Document summarization has been widely studied for many years. Existing methods mainly use statistical or linguistic information to extract the most informative sentences from document. However, those methods ignore the relationship between different granularities (i.e., word, sentence, and topic). Actually, the interactions between those granularities can be used in document summarization. In this paper we proposed a document summarization method based on heterogeneous graph. The method is first implemented by constructing a graph which reflect relationship between different size of granularity nodes, and then using ranking algorithm to calculate score of nodes. Finally, highest score of sentences in the document will be chosen as summary. Experimental results show that our approach outperforms baseline methods.

22 citations

01 Sep 2000
TL;DR: A query-relevant text summary system based on interactive learning that extracts the most relevant sentences of a document with regard to a user query using a classical tf-idf term weighting scheme and learns the user feedback in order to improve its performances.
Abstract: This paper describes a query-relevant text summary system based on interactive learning. The system proceeds in two steps, it first extracts the most relevant sentences of a document with regard to a user query using a classical tf-idf term weighting scheme, it then learns the user feedback in order to improve its performances. Learning operates at two levels: query expansion and sentence scoring.

22 citations

Journal ArticleDOI
TL;DR: It is shown that a fuzzy logic‐based approach to linguistic data summarization can be a simple yet efficient solution in this respect, and various possible protoforms of linguistic summaries represented by protoforms in the form of linguistically quantified propositions are presented.
Abstract: We present a novel approach to linguistic data summarization for numeric data, ie, of the numbers to text type Linguistic summarization is meant as a process of a comprehensive description of big and complex datasets via short statements in natural language First, we briefly survey main developments in the traditional, well developed, and powerful approach to linguistic data summarization based on tools and techniques of natural language generation NLG, notably due to Reiter and his collaborators We indicate that this approach has a serious limitation on the representation and processing of imprecision that is characteristic for natural languages We show that a fuzzy logic-based approach to linguistic data summarization can be a simple yet efficient solution in this respect We present the linguistic summaries represented by protoforms in the form of linguistically quantified propositions dealt with using tools and techniques of fuzzy logic to grasp an inherent imprecision of natural language Such linguistic data summaries can provide a human user, whose only natural means of articulation and communication is natural language, with a simple yet effective and efficient means for the representation and manipulation of knowledge about processes and systems We concentrate on the linguistic summarization of dynamic processes and systems, dealing with data represented as time series We extend the basic, static data-oriented concept of a linguistic data summary to the case of time series data, present various possible protoforms of linguistic summaries, and an analysis of their properties and ways of generation We show two our own real applications of the new tools of linguistic summarization of time series, for the summarization of quotations of an investment mutual fund, and of Web server logs, to show the power of the tool We also mention some other applications known from the literature We conclude with some remarks on the strength of the linguistic summarization for broadly perceived data mining and knowledge discovery and some possible further research directions WIREs Data Mining Knowl Discov 2016, 6:37-46 doi: 101002/widm1175

21 citations

Proceedings ArticleDOI
01 Sep 2017
TL;DR: A novel interactive summarization system that is based on abstractive summarization, derived from a recent consolidated knowledge representation for multiple texts, providing a bullet-style summary while allowing to attain the most important information first and interactively drill down to more specific details.
Abstract: We present a novel interactive summarization system that is based on abstractive summarization, derived from a recent consolidated knowledge representation for multiple texts. We incorporate a couple of interaction mechanisms, providing a bullet-style summary while allowing to attain the most important information first and interactively drill down to more specific details. A usability study of our implementation, for event news tweets, suggests the utility of our approach for text exploration.

21 citations


Network Information
Related Topics (5)
Natural language
31.1K papers, 806.8K citations
85% related
Ontology (information science)
57K papers, 869.1K citations
84% related
Web page
50.3K papers, 975.1K citations
83% related
Recurrent neural network
29.2K papers, 890K citations
83% related
Graph (abstract data type)
69.9K papers, 1.2M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202374
2022160
202152
202061
201947
201852