?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Cr%C3%A9ation+de+surcouche+de+documents+hypertextes+et+traitement+du+langage+naturel&rft.creator=Nadeau%2C+David&rft.subject=Language&rft.description=Cet+article+pr%C3%A9sente+une+extension+aux+algorithmes+de+%0Acr%C3%A9ation+de+surcouche+de+documents+hypertextuels.+%0AIl+s%E2%80%99agit+de+diversifier+la+granularit%C3%A9+de+%0Al%E2%80%99information+qu%E2%80%99il+est+possible+de+capturer+en+%0Autilisant+des+techniques+de+traitement+du+langage+%0Anaturel.+Une+surcouche+de+document+Web+(web+page+wrapper)+%0Aest+une+vue+sur+des+noeuds+HTML+contenant+une+information+%0Adonn%C3%A9e+et+d%C3%A9sir%C3%A9e.+Par+exemple%2C+dans+une+manchette+de+%0Ajournal%2C+une+surcouche+peut+baliser+le+nom+de+l%E2%80%99auteur%2C+%0Ala+date+ou+m%C3%AAme+toutes+les+r%C3%A9f%C3%A9rences+%C3%A0+un+lieu+ou+a+%0Aune+compagnie+quelconque.+Nous+avons+%C3%A9tendu+le+%0Afonctionnement+d%E2%80%99un+algorithme+de+cr%C3%A9ation+de+%0Asurcouchage+afin+de+d%C3%A9passer+la+limite+des+noeuds+HTML+%0Aet+d%E2%80%99extraire+de+l%E2%80%99information+du+contenu+textuel+qui+%0As%E2%80%99y+retrouve.+Nous+appliquons+cette+technique+%C3%A0+la+%0Acr%C3%A9ation+automatique+de+lexiques+(liste+de+mots).&rft.date=2005&rft.type=Conference+Paper&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F4604%2F1%2Fnadeau05surcouchage-final.pdf&rft.identifier=++Nadeau%2C+David++(2005)+Cr%C3%A9ation+de+surcouche+de+documents+hypertextes+et+traitement+du+langage+naturel.++%5BConference+Paper%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F4604%2F