<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">De Pauw, Guy</style></author><author><style face="normal" font="default" size="100%">Peter Waiganjo Wagacha</style></author><author><style face="normal" font="default" size="100%">Gilles-Maurice de Schryver</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Václav Matoušek</style></author><author><style face="normal" font="default" size="100%">Pavel Mautner</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Automatic diacritic restoration for resource-scarce languages</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of Text, Speech and Dialogue, Tenth International Conference</style></secondary-title><tertiary-title><style face="normal" font="default" size="100%">Lecture Notes in Computer Science</style></tertiary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Cilubà</style></keyword><keyword><style  face="normal" font="default" size="100%">diacritics</style></keyword><keyword><style  face="normal" font="default" size="100%">encoding</style></keyword><keyword><style  face="normal" font="default" size="100%">Gĩkũyũ</style></keyword><keyword><style  face="normal" font="default" size="100%">Kikamba</style></keyword><keyword><style  face="normal" font="default" size="100%">machine learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Northern Sotho</style></keyword><keyword><style  face="normal" font="default" size="100%">Sesotho sa Leboa</style></keyword><keyword><style  face="normal" font="default" size="100%">Tshivenda</style></keyword><keyword><style  face="normal" font="default" size="100%">Venda</style></keyword><keyword><style  face="normal" font="default" size="100%">Yoruba</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2007</style></year></dates><urls><related-urls><url><style face="normal" font="default" size="100%">http://aflat.org/files/46290170.pdf</style></url></related-urls></urls><publisher><style face="normal" font="default" size="100%">Springer Berlin / Heidelberg</style></publisher><pub-location><style face="normal" font="default" size="100%">Heidelberg, Germany</style></pub-location><volume><style face="normal" font="default" size="100%">4629</style></volume><pages><style face="normal" font="default" size="100%">170-179</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">The orthography of many resource-scarce languages includes diacritically marked characters. Falling outside the scope of the standard Latin encoding, these characters are often represented in digital language resources as their unmarked equivalents. This renders corpus compilation more difficult, as these languages typically do not have the benefit of large electronic dictionaries to perform diacritic restoration. This paper describes experiments with a machine learning approach that is able to automatically restore diacritics on the basis of local graphemic context.We apply the method to the African languages of Cilubà, Gĩkũyũ, Kĩkamba, Maa, Sesotho sa Leboa, Tshivenda and Yoruba and contrast it with experiments on Czech, Dutch, French, German and Romanian, as well as Vietnamese and Chinese Pinyin.</style></abstract><work-type><style face="normal" font="default" size="100%">inproceedings</style></work-type></record></records></xml>
