Summarization: (1) Using MMR for Diversity- Based Reranking and (2) Evaluating Summaries

Jade Goldstein-Stewart, J. Carbonell
{"title":"Summarization: (1) Using MMR for Diversity- Based Reranking and (2) Evaluating Summaries","authors":"Jade Goldstein-Stewart, J. Carbonell","doi":"10.3115/1119089.1119120","DOIUrl":null,"url":null,"abstract":"This paper develops a method for combining query-relevance with information-novelty in the context of text retrieval and summarization. The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in reranking retrieved documents and in selecting appropriate passages for text summarization. Preliminary results indicate some benefits for MMR diversity ranking in ad-hoc query and in single document summarization. The latter are borne out by the trial-run (unofficial) TREC-style evaluation of summarization systems. However, the clearest advantage is demonstrated in the automated construction of large document and non-redundant multi-document summaries, where MMR results are clearly superior to non-MMR passage selection. This paper also discusses our preliminary evaluation of summarization methods for single documents.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"39","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"NIST's TIPSTER Text Program","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3115/1119089.1119120","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 39

Abstract

This paper develops a method for combining query-relevance with information-novelty in the context of text retrieval and summarization. The Maximal Marginal Relevance (MMR) criterion strives to reduce redundancy while maintaining query relevance in reranking retrieved documents and in selecting appropriate passages for text summarization. Preliminary results indicate some benefits for MMR diversity ranking in ad-hoc query and in single document summarization. The latter are borne out by the trial-run (unofficial) TREC-style evaluation of summarization systems. However, the clearest advantage is demonstrated in the automated construction of large document and non-redundant multi-document summaries, where MMR results are clearly superior to non-MMR passage selection. This paper also discusses our preliminary evaluation of summarization methods for single documents.
总结:(1)利用MMR进行基于多样性的重新排序;(2)评估总结
本文提出了一种在文本检索和摘要中结合查询相关性和信息新颖性的方法。最大边际相关性(MMR)标准致力于减少冗余,同时在重新排序检索文档和选择适当段落进行文本摘要时保持查询相关性。初步结果表明,在特别查询和单文档摘要中,MMR多样性排序具有一定的优势。后者由试运行的(非官方的)trec式总结系统评估证实。然而,最明显的优势体现在大型文档和非冗余多文档摘要的自动构建中,其中MMR结果明显优于非MMR段落选择。本文还讨论了我们对单个文档摘要方法的初步评价。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书