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
26 Apr 2010
TL;DR: This paper focuses on a corpus of instructional documentary video and seeks to improve automatic video summaries by understanding what features in the video catch the eyes and ears of human assessors, and using these findings to inform automatic summarization algorithms.
Abstract: Video summarization is a mechanism for generating short summaries of the video to help people quickly make sense of the content of the video before downloading or seeking more detailed information. To produce reliable automatic video summarization algorithms, it is essential to first understand how human beings create video summaries with manual efforts. This paper focuses on a corpus of instructional documentary video, and seeks to improve automatic video summaries by understanding what features in the video catch the eyes and ears of human assessors, and using these findings to inform automatic summarization algorithms. The paper contributes a thorough and valuable methodology for performing automatic video summarization, and the methodology can be extended to inform summarization of other video corpuses.
8 citations
21 Sep 2021
TL;DR: The CLEF 2021 SimpleText track as discussed by the authors addresses the opportunities and challenges of text simplification approaches to improve scientific information access head-on, and provides appropriate data and benchmarks, starting with pilot tasks in 2019 and creating a community of NLP and IR researchers working together to resolve one of the greatest challenges of today.
Abstract: Information retrieval has moved from traditional document retrieval in which search is an isolated activity, to modern information access where search and the use of the information are fully integrated. But non-experts tend to avoid authoritative primary sources such as scientific literature due to their complex language, internal vernacular, or lacking prior background knowledge. Text simplification approaches can remove some of these barriers, thereby avoiding that users rely on shallow information in sources prioritizing commercial or political incentives rather than the correctness and informational value. The CLEF 2021 SimpleText track addresses the opportunities and challenges of text simplification approaches to improve scientific information access head-on. We aim to provide appropriate data and benchmarks, starting with pilot tasks in 2021, and create a community of NLP and IR researchers working together to resolve one of the greatest challenges of today.
8 citations
01 Jul 2017
TL;DR: In this research, an extractive-based approach is used to generate a two-level summary from online news articles to understand the variation in related news articles from different news agencies.
Abstract: People tend to read multiple news articles on a topic since a single article may not contain all important information. A summary of all the articles related to topic will save the time and energy. Text Summarization is a way of minimizing a textual document to a meaningful summary. In this research, an extractive-based approach is used to generate a two-level summary from online news articles. News topics covered include politics, sports health, science and movie reviews from Fox News from USA, NZ Herald from New Zealand, Hindustan Times from India, BBC from UK, etc. The first-level summary generates the summary of each article on all these topics. Sentiment Analysis is performed on the first-level summary to understand the variation in related news articles from different news agencies. The second-level summary generates the summary of the combined first-level summaries of two/three related articles on a topic. The ROUGE metric is used to evaluate the performance of summarization.
8 citations
18 Jun 2007
TL;DR: A news articles clustering and summarization system that provides integrated access to news articles from various news sites and its efficient summarization technique to handle large amounts of crawled news articles is described.
Abstract: This paper proposes a news articles clustering and summarization system. It provides integrated access to news articles from various news sites. The system consists of a crawler, topic detector, and summarizer. This paper describes its efficient summarization technique to handle large amounts of crawled news articles.
8 citations
Journal Article•
TL;DR: This paper presents an improved and practical approach to automatically summarizing unstructured document by extracting the most relevant sentences from plain text or html version of original document using statistical method and WordNet.
Abstract: This paper presents an improved and practical approach to automatically summarizing unstructured document by extracting the most relevant sentences from plain text or html version of original document. This technique proposed is based upon Key Sentences using statistical method and WordNet. Experimental results show that our approach compares favourably to a commercial text summarizer, and some refinement techniques improves the summarization quality significantly.
8 citations