| 1. | Chinese chunk parsing base on hownet
的汉语组块分析 |
| 2. | The research on reduced feature dimension based on hownet similarity computing
基于知网语义相似度计算的特征降维方法研究 |
| 3. | Using the semantic relation in hownet , it computed the similitude degree to combine the synonymousness
最后本文还讨论了系统的评价方法和系统的实验结果。 |
| 4. | Secondly , the entity models are classified based on the hyponymy relationship of sememes in hownet
然后,基于hownet中实体类义原的上下位关系对实体模型进行了分类。 |
| 5. | And , an algorithm for constructing lexical chains based on hownet knowledge database is given
通过计算词义相似度首先构建词汇链，然后结合词频与区域特征进行关键词选择。 |
| 6. | And last , it mainly lays emphasis on the research of chinese text clustering . it designs a concept clustering algorithm based on the hownet
然后,针对中文文本的聚类,本文设计了以知网为背景知识的概念聚类算法。 |
| 7. | First we put forward the general idea about this method and give a brief introduce to its semantic knowledge resource - the hownet dictionary
本文首先提出了这种方法的总体思路，并对其语义知识资源《知网》作了简要的介绍。 |
| 8. | Specifically , my work includes three parts , the following details : 1 . the tts entity - model database is built based on hownet
具体地讲,本文研究从如下三个方面展开: 1 、研究基于hownet的tts (文景转换)实体模型库的构建。 |
| 9. | In this paper , we present a new method on feature extraction which uses hownet as semantic resource , and use maximum entropy model to realize it
本文提出了一种使用知网作为语义资源选取分类特征，并使用最大熵模型进行分类的新方法。 |
| 10. | The experiment result show that the first sememes in hownet can express the main meaning of the question focus words , it can be as an important feature
实验结果表明，在知网中选取的首义原能很好的表达问题焦点词的语义信息，可作为问题分类的一个主要特征。 |
