| 释义 |
Treebank ˈtri:bænk BNC²³⁶²¹³⁺¹
基本例句
n.树种库¹⁰⁰
The Treebank has size of 1000 thousand Chinese characters.该树库目前已有100万汉字的规模。
Experiments show that small addition of convertedtreebankcan improve the performance of dependency parser, while large addition will bring it down.经过细致分析，我们认为，作为一种利用多种树库提高依存句法分析器性能的方法，短语转依存还存在很多需要深入研究的方面。
Comparative experiments on Hit Chinese Treebank corpus show that the new method shows better performance than current Chinese dependency methods, with precision reaching to 86.4%.在对哈工大中文树库语料上的对比测试结果表明，该方法的依存分析精度达到86.;4%，具有很强的依存分析能力。
In this paper, we compare action-based dependency parsers with complex parsing methods such as generative and discriminative parsers on the standard data set of Penn Chinese Treebank.本文将决策式句法分析同产生式、判别式句法分析这些复杂模型做了比较，试验数据采用宾州中文树库。
An F1 score of 85.5% is achieved by using the evaluation dataset of Chinesetreebankof Beijing university, and obviously better than those of hidden Markov model and maximum entropy Markov model.使用北京大学中文树库的测试结果为F1=85.;5%，高于隐马尔可夫模型和最大熵马尔可夫模型。
With the support of our Chinesetreebankincluding 64426 words, this paper designs and implements a method for automatic prediction of Chinese phrase boundary location based on neural network.在一个含有64426词的汉语树库的支持下，本文设计并实现了基于神经元网络的汉语短语边界自动识别模型。 |