一种基于句子分割的文法自动推导算法 | |
张合 ; 邬晓钧 ; 王晓东 ; 郑方 ; Zhang He ; Wu Xiaojun ; Wang Xiaodong ; Thomas Fang Zheng | |
2010-07-15 ; 2010-07-15 | |
会议名称 | 第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会论文摘要集 ; Abstract Book of the 10~(th) National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing ; 第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会 ; The 10~(th) the National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing ; 中国甘肃兰州 ; CNKI ; 中国中文信息学会语音信息专业委员会、中国声学学会语言、听觉和音乐声学分会、中国语言学会语音学分会 |
关键词 | 口语对话系统 上下文无关增强文法 文法推导 spoken dialogue systems enhanced context free grammar grammar inference TP391.1 |
其他题名 | A method for automatic grammar inference based on sentence segmentation |
中文摘要 | 信息咨询口语对话系统中的领域文法规则往往需要专家来人工设计。本文针对一种面向汉语口语的上下文无关增强文法,提出了一种基于句子分割的文法自动推导算法。其基本思想是:用初始规则集对训练例句进行分析,若不能得到完整的语法树,则先对分析结果进行消歧和归一化,然后根据顶层成分递归地推导出缺少的规则,并更新已有的规则集。为了提高最终文法的性能,本文在例句处理顺序和规则更新上对算法基本流程做了改进。我们在天气预报查询领域进行了实验,结果文法的句法分析准确率在初始规则集为空时达到了64.8%,在初始规则集只包含日期相关规则时达到了86.4%。; The grammar is often manually designed by experts for spoken dialogue systems for information enquiry. A method for automatic grammar inference based on sentence segmentation is proposed in this paper, which adopts a type of enhanced context free grammar for Chinese spoken language. The main idea is to parse the training sentences with an initial rule set. If the parsed syntactic tree is incomplete, the top-most constituents are used to recursively infer the missing rules after disambiguation and normalization, and then the rule set is updated. In order to improve the output grammar, the processing order of the training sentences is adjusted and the method’s process is refined. Some experiments have been done for evaluation in the domain of weather forecast enquiry. The parsing accuracy of the output grammar achieved 64.8% with an empty initial rule set and 86.4% with an initial rule set only including rules for date description.; 国家高技术研究发展计划(863计划)资助(课题编号:2007AA01Z173) |
会议录出版者 | 清华大学 |
语种 | 中文 ; 中文 |
内容类型 | 会议论文 |
源URL | [http://hdl.handle.net/123456789/70801] ![]() |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | 张合,邬晓钧,王晓东,等. 一种基于句子分割的文法自动推导算法[C]. 见:第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会论文摘要集, Abstract Book of the 10~(th) National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing, 第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会, The 10~(th) the National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing, 中国甘肃兰州, CNKI, 中国中文信息学会语音信息专业委员会、中国声学学会语言、听觉和音乐声学分会、中国语言学会语音学分会. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论