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 published on a yearly basis
Papers
More filters
••
01 Oct 2014TL;DR: A novel graph based technique for topic based multidocument summarization by transforming documents into a bipartite graph where one set of node represents entities and the other set of nodes represents sentences.
Abstract: In this paper, we introduce a novel graph based technique for topic based multidocument summarization. We transform documents into a bipartite graph where one set of nodes represents entities and the other set of nodes represents sentences. To obtain the summary we apply a ranking technique to the bipartite graph which is followed by an optimization step. We test the performance of our method on several DUC datasets and compare it to the stateof-the-art.
17 citations
•
TL;DR: In this article, a memory network parameterized sequential determinantal point process is proposed to attend the user query onto different video frames and shots to evaluate the performance of a video summarizer.
Abstract: Recent years have witnessed a resurgence of interest in video summarization. However, one of the main obstacles to the research on video summarization is the user subjectivity - users have various preferences over the summaries. The subjectiveness causes at least two problems. First, no single video summarizer fits all users unless it interacts with and adapts to the individual users. Second, it is very challenging to evaluate the performance of a video summarizer.
To tackle the first problem, we explore the recently proposed query-focused video summarization which introduces user preferences in the form of text queries about the video into the summarization process. We propose a memory network parameterized sequential determinantal point process in order to attend the user query onto different video frames and shots. To address the second challenge, we contend that a good evaluation metric for video summarization should focus on the semantic information that humans can perceive rather than the visual features or temporal overlaps. To this end, we collect dense per-video-shot concept annotations, compile a new dataset, and suggest an efficient evaluation method defined upon the concept annotations. We conduct extensive experiments contrasting our video summarizer to existing ones and present detailed analyses about the dataset and the new evaluation method.
17 citations
•
TL;DR: Researchers tried to generate an automatic abstract of the gigantic body of data from the commencement of the last half century for salient information retrieval from huge amount electronic text.
Abstract: In the time of overloaded online information, automatic text summarization is especially demanded for salient information retrieval from huge amount electronic text. For the blessing of World Wide Web, the mass of data is now enormous in its volume. Researchers realized this fact from various aspects and tried to generate an automatic abstract of the gigantic body of data from the commencement of the last half century. Numerous ways are there for characterizing different approaches to passage recapitulation: extractive and abstractive from single or compound document, objective of content abridgement, characteristic of text summarization, level of processing from superficial to profound and sort of article's content. A significant pr
17 citations
•
22 May 2006TL;DR: A text summarization system that moves beyond standard approaches by using a hybrid approach of linguistic and statistical analysis and by employing text-sort-specific knowledge of document structure and phrases indicating importance is described.
Abstract: We describe a text summarization system that moves beyond standard approaches by using a hybrid approach of linguistic and statistical analysis and by employing text-sort-specific knowledge of document structure and phrases indicating importance. The system is highly modular and entirely XML-based so that different components can be combined easily.
17 citations
••
01 Nov 2000TL;DR: A system for the summarization of multiple text‐only news‐like documents based on a single‐document summarizer that uses text‐extraction to create a summary that presents the information in a logical way and is easy to read.
Abstract: This paper describes a system for the summarization of multiple text-only news-like documents We address two main issues: clustering of documents in order to find the main topics that should be mentioned in the multidocument summary and organization of the information in order to create a summary that presents the information in a logical way and is easy to read The system is based on a single-document summarizer that uses text-extraction
17 citations