助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   词网 的翻译结果: 查询用时:0.013秒
图标索引 在分类学科中查询
所有学科
电信技术
更多类别查询

图标索引 历史查询
 

词网
相关语句
  word-lattice
     Assuming that the 1-best hypothesis is accurate,Lattice-MLLR passes through the word-lattice to accumulate statistics for the MLLR transform estimation procedure.
     Lattice-MLLR是根据解码得到的词网估计MLLR变换参数,词网的潜在误识率远小于识别结果,因此可以使参数估计更为准确。
短句来源
  “词网”译为未确定词的双语例句
     Automatic WordNet Mapping Based on Lexical Knowledge
     以词汇知识驱动的词网自动对映
短句来源
     This paper also points out the initial designing of unique beginner,of wordnet lacks the humanity spirit.
     本文还指出,词网的初始概念的设计缺乏人文性。
短句来源
     Under the decoding strategy of using stack decoding to rescore the word trellis to generate final output,this paper uses decision tree to combine multiple predictors to identify each of recognition output words as correct or incorrect.
     本文在采用堆栈译码词网重估输出作为识别最终输出的连续语音识别实时解码条件下,利用决策树方法将多个预测子融合,对识别输出词进行正确和错误的判别。
短句来源
  相似匹配句对
     THE MESH
    
短句来源
     Hostest Word
     热
短句来源
     NET
     搜
短句来源
     Hotest Word
     热
短句来源
     Information Retrieval Model for the Semantic Web Based on Semantic Index Terms
     基于语义索引的语义信息检索模型
短句来源
查询“词网”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法,我们为您准备了出自英文原文的大量英语例句,供您参考。
  word-lattice
During the second pass, the resulting word-lattice is converted into a word-graph.
      
In this case, adding a predicted class to the word-lattice does not significantly improve word accuracy over the simple n-gram model.
      
Rudnicky and others provided the acoustic data analysis in the word-lattice form.
      
Trial 2 provides as input the word-lattice after intersection with the perceptron-trained n-gram model N.
      


The ontology is a formal explicit specification of a shared conceptualization.The ONTOL-MT system is an ontology for Japanese-Chinese machine translation.This ONTOL-MT system is based on the system of categories proposed by Aristotle.It is useful for the homonym disambiguation.This paper also points out the initial designing of unique beginner,of wordnet lacks the humanity spirit.

知识本体是概念体系的明确规范。ONTOL-MT是我们为研究日汉机器翻译而设计的一个知识本体,在设计这个知识本体时,我们参考了亚里士多德提出的范畴系统,考虑了自然语言处理的人文性,这个知识本体用于同音词的排歧,效果良好。本文还指出,词网的初始概念的设计缺乏人文性。

Under the decoding strategy of using stack decoding to rescore the word trellis to generate final output,this paper uses decision tree to combine multiple predictors to identify each of recognition output words as correct or incorrect.A series of predictors are constructed,including word posterior probability,word length,word posterior probability of neighboring words,13 in all.Optimal combination of predictors is found and best decision tree is constructed for correct-incorrect classification of output words...

Under the decoding strategy of using stack decoding to rescore the word trellis to generate final output,this paper uses decision tree to combine multiple predictors to identify each of recognition output words as correct or incorrect.A series of predictors are constructed,including word posterior probability,word length,word posterior probability of neighboring words,13 in all.Optimal combination of predictors is found and best decision tree is constructed for correct-incorrect classification of output words by testing different combination of predictors and choosing appropriate tree parameters.The experimental results show that the combination of local word posterior probabilities(LWPP) with some of other predictors constructed by this paper,including mainly word length and LWPPs of neighboring words,can give a significant improvement in classification performance,and is better in time consumption and quality than the corresponding results from n-best list.Compared with baseline system,the classification error rate getsan improvement of 41.4%.The experimental results also show that posterior probabilities of neighboring words proposed by this paper are among relatively important predictors.

本文在采用堆栈译码词网重估输出作为识别最终输出的连续语音识别实时解码条件下,利用决策树方法将多个预测子融合,对识别输出词进行正确和错误的判别。本文首先构造了词后验概率、词长、相邻词的后验概率、词的声学和语言得分等共13个预测子,然后利用决策树方法,通过选择不同的预测子组合方式和适当的决策树建树参数,筛选出预测子的最佳组合,建立优化的决策树进行输出词的正误判别。实验结果表明:利用局域词图计算的词后验概率与词长、相邻词的后验概率等几种实时预测子融合后,对识别输出词的正误判别能力得到提高,并且在实时性和分类效果两个方面优于n-best输出的相应结果,相对于基线系统,则分类错误率下降41.4%。实验结果也表明本文提出的相邻词的后验概率是相对重要的预测子。

The lattice-based maximum likelihood linear regression(MLLR) for the unsupervised adaptation algorithm is discussed.Assuming that the 1-best hypothesis is accurate,Lattice-MLLR passes through the word-lattice to accumulate statistics for the MLLR transform estimation procedure.Since the oracle word error rate of word-lattice is much lower than that of the 1-best hypothesis,word-lattice is more likely to provide correct models to estimate the transform.The disadvantage of Lattice-MLLR is that it costs too much...

The lattice-based maximum likelihood linear regression(MLLR) for the unsupervised adaptation algorithm is discussed.Assuming that the 1-best hypothesis is accurate,Lattice-MLLR passes through the word-lattice to accumulate statistics for the MLLR transform estimation procedure.Since the oracle word error rate of word-lattice is much lower than that of the 1-best hypothesis,word-lattice is more likely to provide correct models to estimate the transform.The disadvantage of Lattice-MLLR is that it costs too much computation and storage,so,this paper proposes the two improved measures:(1) compressing the word-lattice;(2) utilizing the information of word time to limit the statistics accumulation.Recognition rate on the national speech recognition evaluation database indicate a relative 3.5% reduction in the word error rate of Lattice-MLLR over traditional MLLR,and the proposed measures can decrease more than 87.9% in computation of Lattice-MLLR.

介绍了一种基于词网的最大似然线性回归(Lattice-MLLR)无监督自适应算法,并进行了改进。Lattice-MLLR是根据解码得到的词网估计MLLR变换参数,词网的潜在误识率远小于识别结果,因此可以使参数估计更为准确。Lattice-MLLR的一个很大缺点是计算量极大,较难实用,对此本文提出了两个改进技术:(1)利用后验概率压缩词网;(2)利用单词的时间信息限制状态统计量的计算范围。实验测定Lattice-MLLR的误识率比传统MLLR相对下降了3.5%,改进技术使Lattice-MLLR计算量下降幅度超过了87.9%。

 
<< 更多相关文摘    
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关词网的内容
在知识搜索中查有关词网的内容
在数字搜索中查有关词网的内容
在概念知识元中查有关词网的内容
在学术趋势中查有关词网的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社