Abstract : In this paper we discuss the technologies for text-to-Pinyin conversion based on context knowledge and D-tree for Mandarin Chinese. The local and long-distance context knowledge were considered and exploited. The context knowledge was represented by regular expressions. D-trees were built based on the regular expressions. The experimental results show that the approach using context knowledge and D-tree is an efficient solution to implement Chinese text-to-Pinyin conversion.
https://hal.inria.fr/inria-00107717
Contributeur : Publications Loria
<>
Soumis le : jeudi 19 octobre 2006 - 09:06:57
Dernière modification le : jeudi 11 janvier 2018 - 06:19:55
Document(s) archivé(s) le : mercredi 29 mars 2017 - 13:14:20
Sen Zhang, Yves Laprie. Text-to-pinyin conversion based on contextual knowledge and D-tree for Mandarin. IEEE International Conference on Natural Language Processing and Knowledge Engineering 2003 - NLP-KE'2003, 2003, Beijing, China, 6 p, 2003. 〈inria-00107717〉
