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
Proceedings Article•
01 Sep 2009TL;DR: This work proposes a new method based on probabilistic latent semantic analysis, which allows for sentences and queries to be represented as probability distributions over latent topics, to estimate the summary relevance of sentences.
Abstract: We consider the problem of query-focused multidocument summarization, where a summary containing the information most relevant to a user’s information need is produced from a set of topic-related documents. We propose a new method based on probabilistic latent semantic analysis, which allows us to represent sentences and queries as probability distributions over latent topics. Our approach combines queryfocused and thematic features computed in the latent topic space to estimate the summaryrelevance of sentences. In addition, we evaluate several dierent similarity measures for computing sentence-level feature scores. Experimental results show that our approach outperforms the best reported results on DUC 2006 data, and also compares well on DUC 2007 data.
95 citations
Posted Content•
04 Jun 2015
TL;DR: This paper proposed an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases, and employed integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary.
Abstract: We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our method first constructs a pool of concepts and facts represented by phrases from the input documents. Then new sentences are generated by selecting and merging informative phrases to maximize the salience of phrases and meanwhile satisfy the sentence construction constraints. We employ integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary. Experimental results on the benchmark data set TAC 2011 show that our framework outperforms the state-of-the-art models under automated pyramid evaluation metric, and achieves reasonably well results on manual linguistic quality evaluation.
95 citations
Posted Content•
TL;DR: A neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner is developed.
Abstract: In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document relationships via an attention mechanism which allows to share information as opposed to simply concatenating text spans and processing them as a flat sequence. Our model learns latent dependencies among textual units, but can also take advantage of explicit graph representations focusing on similarity or discourse relations. Empirical results on the WikiSum dataset demonstrate that the proposed architecture brings substantial improvements over several strong baselines.
94 citations
03 Dec 2013
TL;DR: A novel solution to target-oriented sentiment summarization and SA of short informal texts with a main focus on Twitter posts known as "tweets" is introduced and it is shown that the hybrid polarity detection system not only outperforms the unigram state-of-the-art baseline, but also could be an advantage over other methods when used as a part of a sentiment summarizing system.
Abstract: Sentiment Analysis (SA) and summarization has recently become the focus of many researchers, because analysis of online text is beneficial and demanded in many different applications. One such application is product-based sentiment summarization of multi-documents with the purpose of informing users about pros and cons of various products. This paper introduces a novel solution to target-oriented (i.e. aspect-based) sentiment summarization and SA of short informal texts with a main focus on Twitter posts known as "tweets". We compare different algorithms and methods for SA polarity detection and sentiment summarization. We show that our hybrid polarity detection system not only outperforms the unigram state-of-the-art baseline, but also could be an advantage over other methods when used as a part of a sentiment summarization system. Additionally, we illustrate that our SA and summarization system exhibits a high performance with various useful functionalities and features.
92 citations
TL;DR: SumView is developed, a Web-based review summarization system, to automatically extract the most representative expressions and customer opinions in the reviews on various product features by selecting the most Representative review sentences for each extracted product feature.
Abstract: In this paper, we develop SumView, a Web-based review summarization system, to automatically extract the most representative expressions and customer opinions in the reviews on various product features. Different from existing review analysis which makes more efforts on sentiment classification and opinion mining, our system mainly focuses on summarization, i.e., delivering the majority of information contained in the review documents by selecting the most representative review sentences for each extracted product feature. Comprehensive case studies and experiments demonstrate the effectiveness of our system, and the user study shows users' satisfaction.
92 citations