多文本源信息融合的通用理论第一步:跨文档结构

SIGDIAL Workshop Pub Date : 2000-10-07 DOI:10.3115/1117736.1117745

Dragomir R. Radev

{"title":"多文本源信息融合的通用理论第一步:跨文档结构","authors":"Dragomir R. Radev","doi":"10.3115/1117736.1117745","DOIUrl":null,"url":null,"abstract":"We introduce CST (cross-document structure theory), a paradigm for multi-document analysis. CST takes into account the rhetorical structure of clusters of related textual documents. We present a taxonomy of cross-document relationships. We argue that CST can be the basis for multi-document summarization guided by user preferences for summary length, information provenance, cross-source agreement, and chronological ordering of facts.","PeriodicalId":426429,"journal":{"name":"SIGDIAL Workshop","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2000-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"241","resultStr":"{\"title\":\"A Common Theory of Information Fusion from Multiple Text Sources Step One: Cross-Document Structure\",\"authors\":\"Dragomir R. Radev\",\"doi\":\"10.3115/1117736.1117745\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We introduce CST (cross-document structure theory), a paradigm for multi-document analysis. CST takes into account the rhetorical structure of clusters of related textual documents. We present a taxonomy of cross-document relationships. We argue that CST can be the basis for multi-document summarization guided by user preferences for summary length, information provenance, cross-source agreement, and chronological ordering of facts.\",\"PeriodicalId\":426429,\"journal\":{\"name\":\"SIGDIAL Workshop\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2000-10-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"241\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SIGDIAL Workshop\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3115/1117736.1117745\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIGDIAL Workshop","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3115/1117736.1117745","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 241

摘要

我们介绍了CST(跨文档结构理论)，一个多文档分析的范例。CST考虑了相关语篇簇的修辞结构。我们提出了跨文档关系的分类。我们认为，CST可以作为多文档摘要的基础，根据用户对摘要长度、信息来源、跨源协议和事实的时间顺序的偏好进行指导。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

A Common Theory of Information Fusion from Multiple Text Sources Step One: Cross-Document Structure

We introduce CST (cross-document structure theory), a paradigm for multi-document analysis. CST takes into account the rhetorical structure of clusters of related textual documents. We present a taxonomy of cross-document relationships. We argue that CST can be the basis for multi-document summarization guided by user preferences for summary length, information provenance, cross-source agreement, and chronological ordering of facts.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

SIGDIAL Workshop

自引率

0.00%

发文量