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
Journal Article•
TL;DR: The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in re-ranking retrieved documents and in selecting appropriate passages for text stigmatization.
Abstract: With the continuing growth of online information, it has become increasingly important to provide improved mechanisms to find information quickly. A novel query expansion method to improve the average precision of the original query for information retrieval. The scheme uses a graph-based algorithm to choose sentences in a manner which is different from existing sentence-based query expansion methods. The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in re-ranking retrieved documents and in selecting appropriate passages for text stigmatization.
23 Dec 2022
TL;DR: In this paper , the authors combine extractive summarization and generative summarization to improve the quality of the generative text compared with extractive text, and can significantly improve the generator speed compared with the former.
Abstract: Extractive summarization and generative summarization are the two main ways to generate summarization.However,previous work treats both of them as two independent subtasks.In this paper,we obtain new summarization by combining extractive summarization and generative summarization.This method extracts the key information of the article firstly,and then generates the summarization of the extracted information.The experimental result shows that this method can significantly improve the quality of the generative text compared with extractive summarization,and can significantly improve the generative speed compared with generative summarization.
TL;DR: This article presented a method for summarizing multi-document news web pages based on similarity models and sentence ranking, where relevant sentences are extracted from the original article, where they collected from five news websites that cover the same topic and event.
Abstract: In the area of text summarization, there have been significant advances recently. In the meantime, the current trend in text summarization is focused more on news summarization. Therefore, developing a synthesis approach capable of extracting, comparing, and ranking sentences is vital to create a summary of various news articles in the context of erroneous online data. It is necessary, however, for the news summarization system to be able to deal with multi-document summaries due to content redundancy. This paper presents a method for summarizing multi-document news web pages based on similarity models and sentence ranking, where relevant sentences are extracted from the original article. English-language articles are collected from five news websites that cover the same topic and event. According to our experimental results, our approach provides better results than other recent methods for summarizing news.
20 Aug 2022
TL;DR: The multimodal summarization task can effectively reduce users' information burden and improve user's information acquisition speed by integrating visual and auditory modal information and using the mutual supplement and verification of different modal data as discussed by the authors .
Abstract: With the rapid development of information technology, Internet data is growing exponentially, which makes it difficult for users to extract key information from massive Internet data. Data compression technology represented by text summary has gradually attracted extensive attention from academia and industry. As an extension of text summarization, multimodal summarization task can effectively reduce users’ information burden and improve users’ information acquisition speed by integrating visual and auditory modal information and using the mutual supplement and verification of different modal data. It has high research value in the fields of information retrieval, public opinion analysis, content review and so on. This paper combs the related research of multimodal summarization in recent years, summarizes the existing technologies and related data sets for multimodal summarization tasks, and summarizes the development direction of future research in this field.
16 Dec 2022
TL;DR: In this paper , an extractive technique of text summarization using a sentence clustering approach has been proposed, where the hybrid approach deals with the novel method for comprising of document and sentence clusters using Jaccard and Cosine similarity method.
Abstract: Text summarization is process of getting summaries of multiple documents. Text summarization is very much essential for saving time and resources. Through text summarization knowledge can be grasped quickly. Getting summery is challenging process because relevant information needs to be retrieved. Text summaries essential to resolve the issues of information overload which demands access to reliable and properly crafted summaries. Users can quickly find the information they need using data minimization. Saving the time and effort from having to browse through the entire collection of documents is main advantage of text summarization. In this paper it is focussed on an extractive technique of text summarization using a sentence clustering approach. The hybrid approach deals with the novel method for comprising of document and sentence clustering using Jaccard and Cosine similarity method.