NIST's TIPSTER Text Program最新文献

筛选
英文 中文
Summarization: (1) Using MMR for Diversity- Based Reranking and (2) Evaluating Summaries 总结:(1)利用MMR进行基于多样性的重新排序;(2)评估总结
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119120
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":"https://doi.org/10.3115/1119089.1119120","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":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123787175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 39
TIPSTER Phase III Accomplishments TIPSTER III期成果
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119092
F. Gee
{"title":"TIPSTER Phase III Accomplishments","authors":"F. Gee","doi":"10.3115/1119089.1119092","DOIUrl":"https://doi.org/10.3115/1119089.1119092","url":null,"abstract":"The TIPSTER Text Program Phase III continued the sponsorship of research and development to advance state-of-the-art technologies for text handling and facilitation of cooperation among research and development components from industrial, academic and the U.S. Government.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131917302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Research in Information Extraction: 1996-98 信息抽取研究(英文版);1996- 1998
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119105
R. Grishman
{"title":"Research in Information Extraction: 1996-98","authors":"R. Grishman","doi":"10.3115/1119089.1119105","DOIUrl":"https://doi.org/10.3115/1119089.1119105","url":null,"abstract":"Information extraction involves picking out specified types of information from natural language text. Recent Message Understanding Conferences [1,2,3] have developed a spectrum of such tasks, and we have worked on two of them, at opposite ends of the spectrum: the named entity task, which involves identifying and classifying names, and the scenario template task, which involves extracting critical information (participants, location, date, etc.) about specified classes of events.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132237908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Algorithms that Learn to Extract Information BBN: TIPSTER Phase III 学习提取信息的算法BBN: TIPSTER第三阶段
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119107
Scott Miller, Michael Crystal, Heidi Fox, L. Ramshaw, R. Schwartz, Rebecca Stone, R. Weischedel
{"title":"Algorithms that Learn to Extract Information BBN: TIPSTER Phase III","authors":"Scott Miller, Michael Crystal, Heidi Fox, L. Ramshaw, R. Schwartz, Rebecca Stone, R. Weischedel","doi":"10.3115/1119089.1119107","DOIUrl":"https://doi.org/10.3115/1119089.1119107","url":null,"abstract":"All of BBN's research under the TIPSTER III program has focused on doing extraction by applying statistical models trained on annotated data, rather than by using programs that execute hand-written rules. Within the context of MUC-7, the SIFT system for extraction of template entities (TE) and template relations (TR) used a novel, integrated syntactic/semantic language model to extract sentence level information, and then synthesized information across sentences using in part a trained model for cross-sentence relations. At the named entity (NE) level as well, in both MET-1 and MUC-7, BBN employed a trained, HMM-based model.The results in these TIPSTER evaluations are evidence that such trained systems, even at their current level of development, can perform roughly on a par with those based on rules hand-tailored by experts. In addition, such trained systems have some significant advantages:• They can be easily ported to new domains by simply annotating fresh data.• The complex interactions that make rule-based systems difficult to develop and maintain can here be learned automatically from the training data.We believe that improved and extended versions of such trained models have the potential for significant further progress toward practical systems for information extraction.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133165429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 15
Multiple & Single Document Summarization using DR-LINK 使用DR-LINK的多个和单个文档摘要
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119122
M. McKenna, E. Liddy
{"title":"Multiple & Single Document Summarization using DR-LINK","authors":"M. McKenna, E. Liddy","doi":"10.3115/1119089.1119122","DOIUrl":"https://doi.org/10.3115/1119089.1119122","url":null,"abstract":"Our Tipster Phase III research objective for the Summarization task is to produce a single summary across multiple documents returned from a search on an information retrieval system. An established set of metrics to evaluate the performance of our system is not available in this field at present, so this research is also developing a procedure to evaluate the summaries we create. We hope to uncover useful metrics and evaluation variables that can be used by others working in this area.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116372464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
An NTU-Approach to Automatic Sentence Extraction for Summary Generation 基于ntu的自动句子抽取摘要生成方法
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119117
Kuang-hua Chen, Sheng Huang, Wen-Cheng Lin, Hsin-Hsi Chen
{"title":"An NTU-Approach to Automatic Sentence Extraction for Summary Generation","authors":"Kuang-hua Chen, Sheng Huang, Wen-Cheng Lin, Hsin-Hsi Chen","doi":"10.3115/1119089.1119117","DOIUrl":"https://doi.org/10.3115/1119089.1119117","url":null,"abstract":"Automatic summarization and information extraction are two important Internet services. MUC and SUMMAC play their appropriate roles in the next generation Internet. This paper focuses on the automatic summarization and proposes two different models to extract sentences for summary generation under two tasks initiated by SUMMAC-1. For categorization task, positive feature vectors and negative feature vectors are used cooperatively to construct generic, indicative summaries. For adhoc task, a text model based on relationship between nouns and verbs is used to filter out irrelevant discourse segment, to rank relevant sentences, and to generate the user-directed summaries. The result shows that the NormF of the best summary and that of the fixed summary for adhoc tasks are 0.456 and 0.447. The NormF of the best summary and that of the fixed summary for categorization task are 0.4090 and 0.4023. Our system outperforms the average system in categorization task but does a common job in adhoc task.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123512009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Japanese IE System and Customization Tool 日语IE系统和定制工具
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119108
Chikashi Nobata, S. Sekine, R. Yangarber
{"title":"Japanese IE System and Customization Tool","authors":"Chikashi Nobata, S. Sekine, R. Yangarber","doi":"10.3115/1119089.1119108","DOIUrl":"https://doi.org/10.3115/1119089.1119108","url":null,"abstract":"This paper reports on the development of the Japanese Information Extraction system and the Japanese Information Extraction customization tool. These systems are based on the corresponding English systems, the Proteus Information Extraction system (Grishman 97) and the Proteus Extraction Tool (Yangarber and Grishman 97), developed at NYU. In this paper, we will, in particular, describe the differences between the Japanese systems and English systems.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131313488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Automatic Text Summarization in TIPSTER 自动文本摘要在TIPSTER
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119119
Therese Firmin, I. Mani
{"title":"Automatic Text Summarization in TIPSTER","authors":"Therese Firmin, I. Mani","doi":"10.3115/1119089.1119119","DOIUrl":"https://doi.org/10.3115/1119089.1119119","url":null,"abstract":"Automatic Text Summarization was added as a major research thrust of the TIPSTER program during TIPSTER Phase III, 1996-1998. It is a natural extension of the previously supported research efforts in Information Extraction (IE) and Information Retrieval (IR). There is considerable interest in automatically producing summaries due, in large part, to the growth of the Internet and the World Wide Web. The TIPSTER program sponsored seven research efforts into text summarization, all with different approaches to the problem.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125964863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
MUC/MET Evaluation Trends MUC/MET评价趋势
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119126
Nancy A. Chinchor
{"title":"MUC/MET Evaluation Trends","authors":"Nancy A. Chinchor","doi":"10.3115/1119089.1119126","DOIUrl":"https://doi.org/10.3115/1119089.1119126","url":null,"abstract":"During the course of the Tipster Program, evaluation methodology for information extraction developed as the technology progressed. Multiple task levels and multiple languages were successful targets of information extraction. Automated scoring and statistical significance algorithms were developed for use in scoring systems and for interannotator agreement measures. The scoring interface allowed both system developers and annotators to analyze errors and improve their work. This software and the marked datasets are now in the public domain. Future projects are being carried out based on simplifications indicated by the data, downstream applications, and tractability of scoring algorithms.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131915033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
The Cornell TIPSTER Phase III Project 康奈尔TIPSTER第三期项目
NIST's TIPSTER Text Program Pub Date : 1998-10-13 DOI: 10.3115/1119089.1119099
F. Gee
{"title":"The Cornell TIPSTER Phase III Project","authors":"F. Gee","doi":"10.3115/1119089.1119099","DOIUrl":"https://doi.org/10.3115/1119089.1119099","url":null,"abstract":"The overall objective of the Cornell University TIPSTER Project was to improve end-user efficiency in information retrieval systems by reducing the amount of text that the user must process [1]. The project focuses on high precision IR, near-duplicate detection and context-dependent summarization. The two main foundations of the research are the latest version of the Smart system for information Retrieval and the Empire system for natural language processing. Smart is an implementation of the vector-space model of information retrieval (IR). Its earlier purpose was to provide a framework to conduct IR research but current developments will make the system easier to use by non-researcher. Empire is a research-oriented system that uses machine learning methods to quickly perform partial parsing of sentences.","PeriodicalId":142914,"journal":{"name":"NIST's TIPSTER Text Program","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133200496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
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×
相关产品
×
本文献相关产品
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