Filters








136,192 Hits in 3.7 sec

Satisfying information needs with multi-document summaries

Sanda Harabagiu, Andrew Hickl, Finley Lacatusu
2007 Information Processing & Management  
Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the  ...  This novel framework for summarization has the advantage of producing highly responsive summaries, as indicated by the evaluation results.  ...  While summaries can provide users with valuable information about the range of information contained in a corpus, multi-document summaries are often of limited value in an information-gathering environment  ... 
doi:10.1016/j.ipm.2007.01.004 fatcat:uujzhptylfci3i4kdjknvn7bpa

A query-based multi-document sentiment summarizer

Maria Soledad Pera, Rani Qumsiyeh, Yiu-Kai Ng
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
summaries that satisfy user's information needs, and (ii) ranks among state-ofthe-art query-based multi-document sentiment summarizers.  ...  Even though QM SS relies on a trained method for identifying users' information needs specified in their queries, QM SS does not require any training for performing the summarization task.  ...  that satisfy users' information needs.  ... 
doi:10.1145/2063576.2063731 dblp:conf/cikm/PeraQN11 fatcat:znl2smdqv5fflip3j5vnbbzzmy

Improving Extractive Multi-Document Text Summarization Through Multi-Objective Optimization

2018 Iraqi Journal of Science  
This coverage model is coupled with a proposed diversity model and defined as a Multi-Objective Optimization (MOO) problem.  ...  Multi-document summarization is an optimization problem demanding optimization of more than one objective function simultaneously.  ...  The two fields which have focused on the effective processing of large amounts of data and extraction of information with high quality and relevance to the user's needs are Data Mining (DM) and Information  ... 
doi:10.24996/ijs.2018.59.4b.19 fatcat:uzub557y5bhqbgggbgtipr67ou

Do summaries help?

Kathleen McKeown, Rebecca J. Passonneau, David K. Elson, Ani Nenkova, Julia Hirschberg
2005 Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '05  
articles, Newsblaster multi-document summaries, and human summaries.  ...  Our results show that, in comparison to source documents only, the quality of reports assembled using Newsblaster summaries was significantly better and user satisfaction was higher with both Newsblaster  ...  ACKNOWLEDGEMENTS We would like to thank Andrew Rosenberg for his help with the statistical analysis in an early stage of the evaluation.  ... 
doi:10.1145/1076034.1076072 dblp:conf/sigir/McKeownPENH05 fatcat:abf3cgweoncszdvykkzomsu62y

An empirical study of information synthesis tasks

Enrique Amigó, Julio Gonzalo, Víctor Peinado, Anselmo Peñas, Felisa Verdejo
2004 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04  
contained in a set of relevant documents, in order to obtain a comprehensive, non redundant report that satisfies the information need.  ...  Two main results are presented: a) the creation of an Information Synthesis testbed with 72 reports manually generated by nine subjects for eight complex topics with 100 relevant documents each; and b)  ...  Lin for his assistance with the ROUGE measure. Thanks also to our volunteers for their valuable cooperation.  ... 
doi:10.3115/1218955.1218982 dblp:conf/acl/AmigoGPPV04 fatcat:2bdg53hbqvbkrgpzd2dplhhpp4

ACM – Attribute Conditioning for Abstractive Multi Document Summarization [article]

Aiswarya Sankar, Ankit Chadha
2022 arXiv   pre-print
A challenge that arises with multi document summarization which is not prevalent in single document summarization is the need to effectively summarize multiple documents that might have conflicting polarity  ...  Each of these approaches has primarily focused on the issues of multi document information synthesis and attention based approaches to extract salient information.  ...  Despite the advances made with these approaches, a significant challenge remains in multi document summarization with respect to how to deal with contradictory information present in the multiple source  ... 
arXiv:2205.03978v1 fatcat:cabaz3tzj5arjfcea7v2bcs7aa

Keyword based Automatic Summarization of HTML Documents

Shivangi Gupta, Mukesh Rawat
2015 International Journal of Computer Applications  
Resulting summary report allows individual users or professional information consumers, to quickly familiarize themselves with information that is contained in a large cluster of documents.  ...  Multi-document summarization creates information reports that are both concise and comprehensive.  ...  INTRODUCTION Information retrieval (IR) can be stated as finding material i.e. documents of an unstructured nature basically text that satisfies an information needed within large collections.  ... 
doi:10.5120/ijca2015906421 fatcat:47jbknwrwjd7bpp6izxsrn6i34

Automatic Tailored Multi-Paper Summarization based on Rhetorical Document Profile and Summary Specification

Masayu Leylia Khodra, Dwi Hendratmo Widyantoro, E. Aminudin Aziz, Bambang Riyanto Trilaksono
2012 Journal of ICT Research and Applications  
In this paper, we extend Teufel's tailored summary to deal with multi information needs.  ...  Our TMPS extracts Rhetorical Document Profile (RDP) from each paper and presents a Plan Language (BPLAN) is introduced as a formalization of Teufel' plan and used to represent representation of user information  ...  In this paper, we extend Teufel's tailored summary to deal with multi-papers and more flexible representation of user information needs.  ... 
doi:10.5614/itbj.ict.2012.6.3.4 fatcat:2l2f3ltumfbc3ph33gtwehcyqa

Multi-Document Information Consolidation (Dagstuhl Seminar 19182)

Ido Daga, Iryna Gurevych, Dan Roth, Amanda Stent, Michael Wagner
2019 Dagstuhl Reports  
and visualize multi-document repositories for decision support; and 4) how to do information validation on multi-document repositories.  ...  This report documents the program and the outcomes of Dagstuhl Seminar 19182 "Multi-Document Information Consolidation".  ...  We argue that quality extractive summaries should contain informative content so that they can be used as document surrogates to answer important questions, thereby satisfying users' information needs.  ... 
doi:10.4230/dagrep.9.4.124 dblp:journals/dagstuhl-reports/DaganGRS19 fatcat:lej5rn6i4vhphjun6hw4uj4sra

MULTI-DOCUMENT SUMMARIZATION BASED ON SENTENCE CLUSTERING IMPROVED USING TOPIC WORDS

Indra Lukmana, Daniel Swanjaya, Arrie Kurniawardhani, Agus Zainal Arifin, Diana Purwitasari
2014 JUTI: Jurnal Ilmiah Teknologi Informasi  
Therefore a method to collect these information into a simple summary is needed.  ...  Among a number of sub-tasks involved in multi-document summarization including sentence extraction, topic detection, representative sentences extraction, and sentence ordering.  ...  Many of these news have same contextual content with other news, and made information redundant. Because of this problem a system for collecting and summarizing these texts is needed.  ... 
doi:10.12962/j24068535.v12i2.a317 fatcat:abpzvq6jhbfxveaj3u4z77avwm

Query Snowball: A Co-occurrence-based Approach to Multi-document Summarization for Question Answering

Hajime Morita, Tetsuya Sakai, Manabu Okumura
2012 IPSJ Online Transactions  
We propose a new method for query-oriented extractive multi-document summarization.  ...  To enrich the information need representation of a given query, we build a co-occurrence graph to obtain words that augment the original query terms.  ...  In particular, query-oriented multi-document summarization is useful for helping the user satisfy his information need efficiently by gathering important pieces of information from multiple documents.  ... 
doi:10.2197/ipsjtrans.5.124 fatcat:i4s6pvqibzcgjf5yopo4r65324

Multi-aspect query summarization by composite query

Wei Song, Qing Yu, Zhiheng Xu, Ting Liu, Sheng Li, Ji-Rong Wen
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
A promising future search scenario should involve: (1) understanding user intents; (2) providing relevant information directly to satisfy searchers' needs, as opposed to relevant pages.  ...  Our method outperforms two baseline methods on generating informative summaries.  ...  In addition, a list of URLs couldn't directly satisfy user information needs.  ... 
doi:10.1145/2348283.2348329 dblp:conf/sigir/SongYXLLW12 fatcat:nrwk5oqspzf2xjpk6so3m5a6bu

What Makes a Good Summary? [chapter]

Qunhua Zhao, Eugene Santos, Hien Nguyen, Ahmed Mohamed
2009 Computational Methods for Counterterrorism  
In this paper, we report our experiment to study the sensitivity of human and multi-document summarization. We use the DUC 2002 collection for multi-document summarization.  ...  Along with research on information retrieval and filtering, text summarization is an effective technique to help intelligent analysts shorten their time to find critical information and make timely decision  ...  Thus, for user-centered summarization, an important task is to identify what kind of the details in information needs to be retrieved and kept in the summary to satisfy the specific user interests according  ... 
doi:10.1007/978-3-642-01141-2_3 fatcat:ok5byri2anaubam7mgfqg436ha

Multi-document Summarization by Information Distance

Chong Long, Minlie Huang, Xiaoyan Zhu, Ming Li
2009 2009 Ninth IEEE International Conference on Data Mining  
This paper describes a novel approach for multi-document update summarization. The best summary is defined as one of which has the minimal information distance to the entire document set.  ...  And the best update summary has the minimal conditional information distance to a document cluster given that a prior document cluster has already been read.  ...  The best summary S best should satisfy the constraint as follows: S best = arg min S i D max (B i , S|A) (8) If m = 0 (A = φ), it will be a traditional multi-document summarization problem.  ... 
doi:10.1109/icdm.2009.107 dblp:conf/icdm/LongHZL09 fatcat:5jfcleuf45exln5msroxb3xesu

Towards Narrative Information Systems [chapter]

Philipp Wille, Christoph Lofi, Wolf-Tilo Balke
2015 Lecture Notes in Computer Science  
Narrative interfaces promise to improve the user experience of interacting with information systems by adapting a powerful communication concept which also comes natural in human interaction.  ...  In this paper, we outline how such a narrative information system which answers queries using elaborate stories can be realized.  ...  system to be able to do as there are several different stories from different perspectives that could be told to satisfy a user's information need.  ... 
doi:10.1007/978-3-319-21042-1_52 fatcat:zvzecavflvfrvglztnxapyspuy
« Previous Showing results 1 — 15 out of 136,192 results