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
Book ChapterDOI
07 Nov 2011
TL;DR: Text Summarization aims to condense the information contained in one or more documents and present it in a more concise way, can be very useful for this purpose.
Abstract: Automatic Text Summarization is a Natural Language Processing task which has experienced great development in recent years, mostly due to the rapid growth of the Internet. Therefore, we need methods and tools that help users to manage large amounts of information. Text Summarization aims to condense the information contained in one or more documents and present it in a more concise way, can be very useful for this purpose. It is the creation of a shortened version of a text by a computer program. The product of this procedure still contains the most important points of the original text.

8 citations

Book ChapterDOI
11 Dec 2002
TL;DR: A hierarchical variable-based framework for multi-document summarization of dissertation abstracts in sociology and psychology is presented and makes use of macro-level and microlevel discourse structure of dissertation Abstracts as well as cross-document structure.
Abstract: This paper reports initial work on developing methods for automatic generation of multi-document summaries of dissertation abstracts in a digital library. The focus is on automatically generating a summary of a set of dissertation abstracts retrieved in response to user query, and presenting the summary using a visualization method. A hierarchical variable-based framework for multi-document summarization of dissertation abstracts in sociology and psychology is presented. The framework makes use of macro-level and microlevel discourse structure of dissertation abstracts as well as cross-document structure. The micro-level structure of problem statements found in a sample of 50 dissertation abstracts was analyzed, and the common features found are described in the paper. A demonstration prototype with a tree-view interface for presenting multi-document abstracts has been implemented.

8 citations

Proceedings ArticleDOI
27 Feb 2019
TL;DR: This paper proposes two alternative grouping techniques based on locality sensitive hashing, approximate nearest neighbor search and a fast clustering algorithm that exhibit linear and log-linear runtime complexity, making them much more scalable.
Abstract: Concept map-based multi-document summarization has recently been proposed as a variant of the traditional summarization task with graph-structured summaries. As shown by previous work, the grouping of coreferent concept mentions across documents is a crucial subtask of it. However, while the current state-of-the-art method suggested a new grouping method that was shown to improve the summary quality, its use of pairwise comparisons leads to polynomial runtime complexity that prohibits the application to large document collections. In this paper, we propose two alternative grouping techniques based on locality sensitive hashing, approximate nearest neighbor search and a fast clustering algorithm. They exhibit linear and log-linear runtime complexity, making them much more scalable. We report experimental results that confirm the improved runtime behavior while also showing that the quality of the summary concept maps remains comparable.

8 citations

Book ChapterDOI
Sayali Kulkarni1, Sheide Chammas1, Wan Zhu1, Fei Sha1, Eugene Ie1 
05 Sep 2021
TL;DR: This paper proposed an approach for automatically generated dataset for both extractive and abstractive summaries and design a neural model SIBERT for extractive summarization that exploits the hierarchical nature of the input.
Abstract: Document summarization compress source document(s) into succinct and information-preserving text. A variant of this is query-based multi-document summarization (q mds) that targets summaries to providing specific informational needs, contextualized to the query. However, the progress in this is hindered by limited availability to large-scale datasets. In this work, we make two contributions. First, we propose an approach for automatically generated dataset for both extractive and abstractive summaries and release a version publicly. Second, we design a neural model SIBERT for extractive summarization that exploits the hierarchical nature of the input. It also infuses queries to extract query-specific summaries. We evaluate this model on CoMSum dataset showing significant improvement in performance. This should provide a baseline and enable using CoMSum for future research on q mds.

8 citations

Book ChapterDOI
14 Sep 2015
TL;DR: This paper carried out two phases of experiments to systematically compare usefulness of different types of opinion summarization techniques, finding that participants preferred Aspect Oriented Sentiments the most and Tag cloud the least.
Abstract: Opinion Summarization research addresses how to help people in making appropriate decisions in an effective way This paper aims to help users in their decision-making by providing them effective opinion presentation styles We carried out two phases of experiments to systematically compare usefulness of different types of opinion summarization techniques In the first crowd-sourced study, we recruited 46 turkers to generate high quality summary information This first phase generated four styles of summaries: Tag Clouds, Aspect Oriented Sentiments, Paragraph Summary and Group Sample In the follow-up second phase, 34 participants tested the four styles in a card sorting experiment Each participant was given 32 cards with 8 per presentation styles and completed the task of grouping the cards into five categories in terms of the usefulness of the cards Results indicated that participants preferred Aspect Oriented Sentiments the most and Tag cloud the least Implications and hypotheses are discussed

8 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