@inproceedings{44643091c1ed43059e69d5f999061dcd,
title = "Chinese personal name recognition using N-gram model and rules",
abstract = "Chinese personal name recognition plays an important role in Chinese word segmentation and it's difficult to recognize whether a sequence of characters is a name or not for its complexity. This paper presents a new algorithm based on N-gram model and recognition rules to resolve this problem. In order to increase efficiency and accuracy, we also build several dictionaries such as a surname dictionary and a person-name dictionary. Experiments on different corpora show that the improved tokenizer using this algorithm performs stably and achieves more than 10 percent word segmentation accuracy increase than the original one. Averagely the improved tokenizer's recall rate and accuracy rate are both over 92\%.",
keywords = "Chinese personal name recognition, N-gram model, recognition rules",
author = "Chen Lin and Zhang Hui and Li Zhen'an",
year = "2012",
language = "英语",
isbn = "9788994364216",
series = "Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012",
pages = "450--453",
booktitle = "Proceedings - 2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012",
note = "2012 7th International Conference on Computing and Convergence Technology (ICCIT, ICEI and ICACT), ICCCT 2012 ; Conference date: 03-12-2012 Through 05-12-2012",
}