Named entity extraction from broadcast news

Named entity extraction from broadcast news. Miller, D., Schwartz, R., Weischedel, R., & Stone, R. In Proceedings DARPA Broadcast News Workshop, pages 37, 1999. Morgan Kaufmann Pub.

Website abstract bibtex

In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present some top level observations and a detailed engineering analysis of our system 's failures and successes. We explore the effects of word error rate, loss of textual clues, amount of training data, changes in guidelines, and out-of-vocabulary errors. 1. Introduction BBN used the IdentiFinder(tm) system (described in [1]) to perform the Named-Entity extraction spoke of the 1998 Hub4 DARPA evaluation. We annotated with named-entity markup the 175 hours of Broadcast News acoustic modelling data, and trained IdentiFinder's statistical models on it. In test, IdentiFinder segmented the input text into paragraphs by splitting at story boundaries (when working from text) or at 1 second silences (when working from speech). Table 1 shows our official evaluation results for all five transcript conditio...

@inProceedings{
 title = {Named entity extraction from broadcast news},
 type = {inProceedings},
 year = {1999},
 identifiers = {[object Object]},
 pages = {37},
 websites = {http://books.google.com/books?hl=en&amp;lr=&amp;id=uuR3mpBI5ksC&amp;oi=fnd&amp;pg=PA37&amp;dq=Named+Entity+Extraction+from+Broadcast+News&amp;ots=DLbCj3OObV&amp;sig=cHU9oCNdybT_wkGnp-9p9I0k0t8},
 publisher = {Morgan Kaufmann Pub},
 id = {863662c4-c373-3066-9068-f99e1b720579},
 created = {2011-12-29T19:53:53.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 tags = {named entities},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Miller1999},
 private_publication = {false},
 abstract = {In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present some top level observations and a detailed engineering analysis of our system 's failures and successes. We explore the effects of word error rate, loss of textual clues, amount of training data, changes in guidelines, and out-of-vocabulary errors. 1. Introduction BBN used the IdentiFinder(tm) system (described in [1]) to perform the Named-Entity extraction spoke of the 1998 Hub4 DARPA evaluation. We annotated with named-entity markup the 175 hours of Broadcast News acoustic modelling data, and trained IdentiFinder's statistical models on it. In test, IdentiFinder segmented the input text into paragraphs by splitting at story boundaries (when working from text) or at 1 second silences (when working from speech). Table 1 shows our official evaluation results for all five transcript conditio...},
 bibtype = {inProceedings},
 author = {Miller, David and Schwartz, Richard and Weischedel, Ralph and Stone, Rebecca},
 booktitle = {Proceedings DARPA Broadcast News Workshop}
}

Downloads: 0

{"_id":"YhXvNsyhSM2qZvWw5","bibbaseid":"miller-schwartz-weischedel-stone-namedentityextractionfrombroadcastnews-1999","downloads":0,"creationDate":"2016-06-29T19:16:08.184Z","title":"Named entity extraction from broadcast news","author_short":["Miller, D.","Schwartz, R.","Weischedel, R.","Stone, R."],"year":1999,"bibtype":"inProceedings","biburl":"http://staffwww.dcs.shef.ac.uk/people/H.Christensen/hclibrary_290116.bib","bibdata":{"title":"Named entity extraction from broadcast news","type":"inProceedings","year":"1999","identifiers":"[object Object]","pages":"37","websites":"http://books.google.com/books?hl=en&lr=&id=uuR3mpBI5ksC&oi=fnd&pg=PA37&dq=Named+Entity+Extraction+from+Broadcast+News&ots=DLbCj3OObV&sig=cHU9oCNdybT_wkGnp-9p9I0k0t8","publisher":"Morgan Kaufmann Pub","id":"863662c4-c373-3066-9068-f99e1b720579","created":"2011-12-29T19:53:53.000Z","file_attached":false,"profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","tags":"named entities","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Miller1999","private_publication":false,"abstract":"In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present some top level observations and a detailed engineering analysis of our system 's failures and successes. We explore the effects of word error rate, loss of textual clues, amount of training data, changes in guidelines, and out-of-vocabulary errors. 1. Introduction BBN used the IdentiFinder(tm) system (described in [1]) to perform the Named-Entity extraction spoke of the 1998 Hub4 DARPA evaluation. We annotated with named-entity markup the 175 hours of Broadcast News acoustic modelling data, and trained IdentiFinder's statistical models on it. In test, IdentiFinder segmented the input text into paragraphs by splitting at story boundaries (when working from text) or at 1 second silences (when working from speech). Table 1 shows our official evaluation results for all five transcript conditio...","bibtype":"inProceedings","author":"Miller, David and Schwartz, Richard and Weischedel, Ralph and Stone, Rebecca","booktitle":"Proceedings DARPA Broadcast News Workshop","bibtex":"@inProceedings{\n title = {Named entity extraction from broadcast news},\n type = {inProceedings},\n year = {1999},\n identifiers = {[object Object]},\n pages = {37},\n websites = {http://books.google.com/books?hl=en&lr=&id=uuR3mpBI5ksC&oi=fnd&pg=PA37&dq=Named+Entity+Extraction+from+Broadcast+News&ots=DLbCj3OObV&sig=cHU9oCNdybT_wkGnp-9p9I0k0t8},\n publisher = {Morgan Kaufmann Pub},\n id = {863662c4-c373-3066-9068-f99e1b720579},\n created = {2011-12-29T19:53:53.000Z},\n file_attached = {false},\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 tags = {named entities},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Miller1999},\n private_publication = {false},\n abstract = {In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present some top level observations and a detailed engineering analysis of our system 's failures and successes. We explore the effects of word error rate, loss of textual clues, amount of training data, changes in guidelines, and out-of-vocabulary errors. 1. Introduction BBN used the IdentiFinder(tm) system (described in [1]) to perform the Named-Entity extraction spoke of the 1998 Hub4 DARPA evaluation. We annotated with named-entity markup the 175 hours of Broadcast News acoustic modelling data, and trained IdentiFinder's statistical models on it. In test, IdentiFinder segmented the input text into paragraphs by splitting at story boundaries (when working from text) or at 1 second silences (when working from speech). Table 1 shows our official evaluation results for all five transcript conditio...},\n bibtype = {inProceedings},\n author = {Miller, David and Schwartz, Richard and Weischedel, Ralph and Stone, Rebecca},\n booktitle = {Proceedings DARPA Broadcast News Workshop}\n}","author_short":["Miller, D.","Schwartz, R.","Weischedel, R.","Stone, R."],"urls":{"Website":"http://books.google.com/books?hl=en&lr=&id=uuR3mpBI5ksC&oi=fnd&pg=PA37&dq=Named+Entity+Extraction+from+Broadcast+News&ots=DLbCj3OObV&sig=cHU9oCNdybT_wkGnp-9p9I0k0t8"},"bibbaseid":"miller-schwartz-weischedel-stone-namedentityextractionfrombroadcastnews-1999","role":"author","downloads":0,"html":""},"search_terms":["named","entity","extraction","broadcast","news","miller","schwartz","weischedel","stone"],"keywords":[],"authorIDs":[],"dataSources":["kQqCE6irCXYpDG9Gc"]}