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.

Summarizing large-scale, multiple-document news data: sparse methods and human validation

Abstract: News media signicantly drives the course of events. Understanding how has long been an active and important area of research. Now, as the amount of online news media available grows, there is even more information calling for analysis, an ever increasing range of inquiry that one might conduct. We believe subject-specic summarization of multiple news documents at once can help. In this paper we adapt scalable statistical techniques to perform this summarization under a predictive framework using a vector space model of documents. We reduce corpora of many millions of words to a few representative key-phrases that describe a specied subject of interest. We propose this as a tool for news media study. We consider the ecacies of four dierent

On the use of hierarchical prediction structures for efficient summary generation of H.264/AVC bitstreams

Abstract: Video summarization refers to an important set of abstraction techniques aimed to provide a compact representation of the video essential to effectively browse and retrieve video content from multimedia repositories Most of these video summarization techniques, such as image storyboards, video skims and fast previews, are based on selecting some frames or segments H264/AVC has become a widely accepted coding standard and is expected that many of the content will be available in this format soon This paper proposes a generic model of video summarization especially suitable for generating summaries of H264/AVC bitstreams in a highly efficient manner, using the concept of temporal scalability via hierarchical prediction structures Along with the model, specific examples of summarization techniques are given to prove the utility of the model

MOpiS: A Multiple Opinion Summarizer

Abstract: Product reviews written by on-line shoppers is a valuable source of information for potential new customers who desire to make an informed purchase decision. Manually processing quite a few dozens, or even hundreds, of reviews for a single product is tedious and time consuming. Although there exist mature and generic text summarization techniques, they are focused primarily on article type content and do not perform well on short and usually repetitive snippets of text found at on-line shops. In this paper, we propose MOpiS, a multiple opinion summarization algorithm that generates improved summaries of product reviews by taking into consideration metadata information that usually accompanies the on-line review text. We demonstrate the effectiveness of our approach with experimental results.

The Mixture of Textrank and Lexrank Techniques of Single Document Automatic Summarization Research in Tibetan

Abstract: Today is an era of knowledge economy and information dominated. Automatic summarization is an important research in the field of natural language processing, its purpose to explore human obtain valuable information from natural language texts. As the Tibetan information processing technology is backward, and the achievements of automatic summarization have not been publicly reported in Tibetan. This paper references the existed Chinese and English automatic summarization technology in domestic and foreign, and proposes a method of Tibetan automatic summarization. Combination with the advantage of keyword processing based on TextRank and processing of the relationship between sentences based on LexRank algorithm. Take full account of the frequency, part of speech, word position, word length, content and position of a sentence. In particular, the generated summarization considering the similarity of candidate sentences. Experiments analysis three summarization methods based on TextRank, based on LexRank and based on LexRank+TextRank respectively, and using the ROUGE value to evaluate the effect of summarization. Experimental results show that, the effect of the mixture of TextRank and LexRank techniques of single document automatic summarization in Tibetan is better and accuracy reached 80%.

Guided Structure-Aware Review Summarization

Abstract: Although the goal of traditional text summarization is to generate summaries with diverse information, most of those applications have no explicit definition of the information structure. Thus, it is difficult to generate truly structure-aware summaries because the information structure to guide summarization is unclear. In this paper, we present a novel framework to generate guided summaries for product reviews. The guided summary has an explicitly defined structure which comes from the important aspects of products. The proposed framework attempts to maximize expected aspect satisfaction during summary generation. The importance of an aspect to a generated summary is modeled using Labeled Latent Dirichlet Allocation. Empirical experimental results on consumer reviews of cars show the effectiveness of our method.