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
09 Oct 2015
TL;DR: The Weibo-oriented Chinese news summarization task aims to automatically generate a short summary for a given Chinese news article, and the short summary is used for news release and propagation on Sina Weibo.
Abstract: The Weibo-oriented Chinese news summarization task aims to automatically generate a short summary for a given Chinese news article, and the short summary is used for news release and propagation on Sina Weibo. The length of the short summary is less than 140 Chinese characters. The task can be considered a special case of single document summarization. In this paper, we will introduce the evaluation dataset, the participating teams and the evaluation results. The dataset has been released publicly.
1 citations
01 Jan 2017
TL;DR: This chapter develops a novel understanding-oriented approach of multimedia news summarization for searching results on Internet that uncovers the underlying topics among the query-related news information and threads the news events within each topic to generate a query- related brief overview.
Abstract: People now live in a sea of massive multimedia data Given results from multimedia news search, there are several underlying topics to cover the stories of the returned results The element “How” can be enhanced by uncovering the underlying topics In this chapter, we develop a novel understanding-oriented approach of multimedia news summarization for searching results on Internet It uncovers the underlying topics among the query-related news information and threads the news events within each topic to generate a query-related brief overview And we design a friendly interface to present users the understanding-oriented hierarchical summarization of their required news information
1 citations
28 May 2015
TL;DR: The experimental result shows the effectiveness of the time features in the extraction process, and a text segmentation method, LCSeg, is utilized to improve the coverage of the summary.
Abstract: In this paper, we propose a method to summarize a multi-party conversation. The method consists of two processes; important utterance extraction and summary generation using the extracted utterances. For the extraction process, we apply time features as new nonverbal information. For the generation process, we utilize a text segmentation method, LCSeg, to improve the coverage of the summary. The experimental result shows the effectiveness of the time features in the extraction process.
1 citations
TL;DR: A series of method for calculating the semantic similarity and thus identifying the features of the text is proposed, based on the calculation of semantic comparability in the how-net.
Abstract: There exists great text information on the internet, and there is still big unknown area in the inspection of the information. How to analyze, forecast and inspect the information will be a new issue in the field of information security. The paper, based on the calculation of semantic comparability in the how-net, proposes a series of method for calculating the semantic similarity and thus identifying the features of the text.
1 citations