Automatic Single-Document Key Fact Extraction from Newswire Articles. Kastner, I. & Monz, C. Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on EACL 09, Association for Computational Linguistics, 2009.
Paper
Website abstract bibtex This paper addresses the problem of extracting the most important facts from a news article. Our approach uses syntactic, semantic, and general statistical features to identify the most important sentences in a document. The importance of the individual features is estimated using generalized iterative scaling methods trained on an annotated newswire corpus. The performance of our approach is evaluated against 300 unseen news articles and shows that use of these features results in statistically significant improvements over a provenly robust baseline, as measured using metrics such as precision, recall and ROUGE.
@article{
title = {Automatic Single-Document Key Fact Extraction from Newswire Articles},
type = {article},
year = {2009},
keywords = {information retrieval & textual information access,natural language processing},
pages = {415-423},
websites = {http://eprints.pascal-network.org/archive/00005591/},
publisher = {Association for Computational Linguistics},
id = {13c4e45d-d440-3787-8563-529dbc8009a5},
created = {2011-02-24T21:47:51.000Z},
file_attached = {true},
profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
last_modified = {2017-03-14T14:36:19.698Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Kastner2009},
private_publication = {false},
abstract = {This paper addresses the problem of extracting the most important facts from a news article. Our approach uses syntactic, semantic, and general statistical features to identify the most important sentences in a document. The importance of the individual features is estimated using generalized iterative scaling methods trained on an annotated newswire corpus. The performance of our approach is evaluated against 300 unseen news articles and shows that use of these features results in statistically significant improvements over a provenly robust baseline, as measured using metrics such as precision, recall and ROUGE.},
bibtype = {article},
author = {Kastner, Itamar and Monz, Christof},
journal = {Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on EACL 09},
number = {April}
}
Downloads: 0
{"_id":"zJamNPXJsyW57XDCd","bibbaseid":"kastner-monz-automaticsingledocumentkeyfactextractionfromnewswirearticles-2009","authorIDs":[],"author_short":["Kastner, I.","Monz, C."],"bibdata":{"title":"Automatic Single-Document Key Fact Extraction from Newswire Articles","type":"article","year":"2009","keywords":"information retrieval & textual information access,natural language processing","pages":"415-423","websites":"http://eprints.pascal-network.org/archive/00005591/","publisher":"Association for Computational Linguistics","id":"13c4e45d-d440-3787-8563-529dbc8009a5","created":"2011-02-24T21:47:51.000Z","file_attached":"true","profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Kastner2009","private_publication":false,"abstract":"This paper addresses the problem of extracting the most important facts from a news article. Our approach uses syntactic, semantic, and general statistical features to identify the most important sentences in a document. The importance of the individual features is estimated using generalized iterative scaling methods trained on an annotated newswire corpus. The performance of our approach is evaluated against 300 unseen news articles and shows that use of these features results in statistically significant improvements over a provenly robust baseline, as measured using metrics such as precision, recall and ROUGE.","bibtype":"article","author":"Kastner, Itamar and Monz, Christof","journal":"Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on EACL 09","number":"April","bibtex":"@article{\n title = {Automatic Single-Document Key Fact Extraction from Newswire Articles},\n type = {article},\n year = {2009},\n keywords = {information retrieval & textual information access,natural language processing},\n pages = {415-423},\n websites = {http://eprints.pascal-network.org/archive/00005591/},\n publisher = {Association for Computational Linguistics},\n id = {13c4e45d-d440-3787-8563-529dbc8009a5},\n created = {2011-02-24T21:47:51.000Z},\n file_attached = {true},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Kastner2009},\n private_publication = {false},\n abstract = {This paper addresses the problem of extracting the most important facts from a news article. Our approach uses syntactic, semantic, and general statistical features to identify the most important sentences in a document. The importance of the individual features is estimated using generalized iterative scaling methods trained on an annotated newswire corpus. The performance of our approach is evaluated against 300 unseen news articles and shows that use of these features results in statistically significant improvements over a provenly robust baseline, as measured using metrics such as precision, recall and ROUGE.},\n bibtype = {article},\n author = {Kastner, Itamar and Monz, Christof},\n journal = {Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics on EACL 09},\n number = {April}\n}","author_short":["Kastner, I.","Monz, C."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfdabac2-d7f2-3c5b-aa7a-06431c0ae35e/file/3811d1d1-4fd9-a9df-0f90-0c6e55b1a484/2009-Automatic_Single-Document_Key_Fact_Extraction_from_Newswire_Articles.pdf.pdf","Website":"http://eprints.pascal-network.org/archive/00005591/"},"bibbaseid":"kastner-monz-automaticsingledocumentkeyfactextractionfromnewswirearticles-2009","role":"author","keyword":["information retrieval & textual information access","natural language processing"],"downloads":0,"html":""},"bibtype":"article","creationDate":"2020-02-06T23:48:11.710Z","downloads":0,"keywords":["information retrieval & textual information access","natural language processing"],"search_terms":["automatic","single","document","key","fact","extraction","newswire","articles","kastner","monz"],"title":"Automatic Single-Document Key Fact Extraction from Newswire Articles","year":2009}