提出了一种汉语句法分析知识自动获取的新方法9 该方法以双语语料库为基础，在双语语言模型的指导下，利用英语句法分析和双语词汇对齐得到汉语句子分析结果9 根据得到的句子分析可以提取汉语组块边界信息和简单的句法分析规则9 实验结果表明，自动获取的组块分析边界和已有的汉语句法分析体系取得了很好的一致性，证明了该方法的可行性和有效性9 文中提出的方法充分利用现有的英语句法研究成果，为汉语句法分析研究提出了一个崭新的思路9

This paper proposes a new method for automatic acquisition of Chinese bracketing knowledge from English-Chinese sentencealigned bilingual corpora. Bilingual sentence pairs are first aligned in syntactic structure by combining English parse trees with a statistical bilingual language model. Chinese bracketing knowledge is then extracted automatically. The preliminary experiments show automatically learned knowledge accords well with manually annotated brackets. The proposed method is particularly useful to acquire bracketing knowledge for a less studied language that lacks tools and resources found in a second language more studied. Although this paper discusses experiments with Chinese and English, the method is also applicable to other language pairs.

未登录词的识别是汉语自动分词中的主要问题。本文以对中国人名，中国地名和外国译名进行整体识别为目标，采用分解处理策略降低了整体处理难度，并使用动态规划方法实现了最佳路径的搜索，较好地解决了未登录词之间的冲突问题。通过对真实语料识别的测试，证明该方法可以全面提高未登录词识别的正确率和召回率。

Finding simplc, non-recursive, base noun phrasc is an important step for many natural language pro-ccssing applications. This paper prescnts a new corpus-based approach using decision tree for that purpose. In contrast to previous methods for Base NP identification, we adopt a decision tree trainedfrom Penn Treebank to identify Base NP. And a self-leaming mechanism is further integrated into our model. Experimental rosults show good performances using our method. The method can also be applied to processing of any other language.

句法结构歧义是句法分析过程中最主要也是最难解决的问题之一。使用了一种组合型的概率评价函数解决英语句法分析过程中所面临的结构歧义问题，综合考虑了句法分析时的结构特性和上下文信息。并使用基于规则的句法分析后校正机制对错误的分析结果进行进一步的校正。组合型的概率评价函数为更精细的句法分析提供了一个可以扩充的统计模型，这种方法也可以适用于其它语言的句法分析。实验结果表明，这种方法具有较高的精确率和召回率。