上海大学学报(英文版)
上海大學學報(英文版)
상해대학학보(영문판)
JOURNAL OF SHANGHAL UNIVERSITY
2003年
2期
148-155
,共8页
language model%pattern recognition%Chinese character recognition
A good language model is essential to a postprocessing algorithm for recognition systems. In the past, researchers have pre-sented various language models, such as character based language models, word based language model, syntactical rules language mod-el, hybrid models, etc. The word N-gram model is by far an effective and efficient model, but one has to address the problem of datasparseness in establishing the model. Katz and Kneser et al. respectively presented effective remedies to solve this challenging prob-lem. In this study, we proposed an improvement to their methods by incorporating Chinese language-specific information or Chineseword class information into the system.
