该文介绍了如何将角色反演算法的思想用在多信息源多语种问答系统中来构建句法分析器。
This paper introduces how to use the concept of Role Inverse Algorithm in order to build syntactic parser in the various information resources based multi-lingual question answering system.
是基于一定语义分析的、以定子句文法作为描述工具的汉语句法分析器，能分析比较复杂的汉语句子。
SYNAC is a syntactic analyzer based on some semantic analysis, which USES Definite Clause Grammar as its expressing tool. It can process more complicate sentences.
实验结果证明，通过选取一半的句子训练出的句法分析器，其性能就能近似于用所有句子训练的句法分析器的性能。
Our result showed that the amount of training sentence could be reduced by 50% with an approximate performance of the statistical parser.
在公共的测试集上对句法分析器的性能进行了评价，对于正确分词和词性标注的句子，句法分析的精确率和召回率分别达到85.89%和85.61%。
The parser was evaluated on the standard test set with PARSEVAL metric. It performed with the precision of 85.89% and the recall rate of 85.61% on the sentences with gold segmentation and POS tagging.
进而将BMP神经网络运用于句法分析，提出神经网络分析器，并与传统方法相比给出了性能代价比分析，显示其优越性。
Then an NN analyzer for syntax analysis is put forward and the analysis for the ratio of performance to cost is given. The result shows that BMP has the superiority to conventional one.
进而将BMP神经网络运用于句法分析，提出神经网络分析器，并与传统方法相比给出了性能代价比分析，显示其优越性。
Then an NN analyzer for syntax analysis is put forward and the analysis for the ratio of performance to cost is given. The result shows that BMP has the superiority to conventional one.
应用推荐