对大规模真实语料的标注实验表明基于转换的方法与三元统计模型方法相得益彰;
Our experiment for the large scale real corpus tagging proves that transformation-based algorithm and tri-gram statistic method bring out the best in each other.
之后,用基于词性的三元边界统计模型和规则相结合的方法识别其它未处理的介词短语。
Secondly the algorithm integrates a statistical model based on part-of-speech and rules to identify the prepositional phrases that haven't been tackled in the first step.
在本文中,我们提出了一种统一的统计语言模型方法用来汉语自动分词和中文命名实体识别,这种方法对基于词的三元语言模型进行了很好的扩展。
In this paper, we extend a word-based trigram modeling to Chinese word segmentation and Chinese named entity recognition, by proposing a unified approach to SLM.
应用推荐