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 ArticleDOI
09 May 2019
TL;DR: This study is the first to compare deep learning techniques on extractive query-focused multi-document summarization and shows that Bi-LSTM with Max-pooling achieves the highest performance among the methods compared.
Abstract: Query-focused multi-document summarization aims to produce a single, short document that summarizes a set of documents that are relevant to a given query. During the past few years, deep learning approaches have been utilized to generate summaries in an abstractive or extractive manner. In this study, we employ six deep neural network approaches to solving a query-focused extractive multi-document summarization task and compare their performances. To the best of our knowledge, our study is the first to compare deep learning techniques on extractive query-focused multi-document summarization. Our experiments with DUC 2005–2007 benchmark datasets show that Bi-LSTM with Max-pooling achieves the highest performance among the methods compared.

4 citations

Book ChapterDOI
14 Dec 2020
TL;DR: In this paper, an interactive concept-based summarization model, called Adaptive Summaries, is proposed to help users make their desired summary instead of producing a single inflexible summary.
Abstract: Exploring the tremendous amount of data efficiently to make a decision, similar to answering a complicated question, is challenging with many real-world application scenarios. In this context, automatic summarization has substantial importance as it will provide the foundation for big data analytic. Traditional summarization approaches optimize the system to produce a short static summary that fits all users that do not consider the subjectivity aspect of summarization, i.e., what is deemed valuable for different users, making these approaches impractical in real-world use cases. This paper proposes an interactive concept-based summarization model, called Adaptive Summaries, that helps users make their desired summary instead of producing a single inflexible summary. The system learns from users’ provided information gradually while interacting with the system by giving feedback in an iterative loop. Users can choose either reject or accept action for selecting a concept being included in the summary with the importance of that concept from users’ perspectives and confidence level of their feedback. The proposed approach can guarantee interactive speed to keep the user engaged in the process. Furthermore, it eliminates the need for reference summaries, which is a challenging issue for summarization tasks. Evaluations show that Adaptive Summaries helps users make high-quality summaries based on their preferences by maximizing the user-desired content in the generated summaries.

4 citations

Posted Content
TL;DR: This work shows how to adapt two sequence prediction models to imitate greedy maximization under knapsack constraint problems: CONSEQOPT (Dey et al., 2012) and SCP (Ross et al, 2013).
Abstract: We study the problem of predicting a set or list of options under knapsack constraint. The quality of such lists are evaluated by a submodular reward function that measures both quality and diversity. Similar to DAgger (Ross et al., 2010), by a reduction to online learning, we show how to adapt two sequence prediction models to imitate greedy maximization under knapsack constraint problems: CONSEQOPT (Dey et al., 2012) and SCP (Ross et al., 2013). Experiments on extractive multi-document summarization show that our approach outperforms existing state-of-the-art methods.

4 citations

Journal ArticleDOI
TL;DR: A fuzzy based incremental clustering by which the selection and deselection of frames are done based on fuzzy rules is used based on users' comments on the video summarization to indicate the high accuracy of summarization and the less computation time.
Abstract: The significant development of multimedia and dijital video production in recent years has led to the mass production of personal and commerical video archives.Therefore, the need for efficient tools and methods of accessing video content and information rapidly is significantly increasing. Video summarization is the removal of visual redundancy and repetitive video frames,and obtaining a short summary of the whole video so that the summary obtained effectively reflects the whole video content. Examples of these summarizations in recent years include STIMO and VSUMM.According to users' comments, in the mentioned methods, the summarization has a high rate of error in a full report of summarization and a low accuracy in non-repetitive frames production, as well as a high computation time.In this paper.in order to solve these problems,we developed a system which modeled users' and supervisors' comments.We used a fuzzy based incremental clustering by which the selection and deselection of frames are done based on fuzzy rules. The extracted rules were determined based on users' comments on the video summarization.Finally, we performed our proposed method on the video clips used in the previous methodes.Produced summaries were evaluated by a qualitative method to minimize human interferences.The results obtained indicate the high accuracy of summarization and the less computation time. DOI: http://dx.doi.org/10.11591/ijece.v4i4.5836

4 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