基于注疏注音信息的词性自动校正  

Automatic Speech Tagging Adjustment Based on the Information of Phonetic Notation in Ancient Texts

在线阅读下载全文

作  者:冯敏萱[1] 刘浏[1] 

机构地区:[1]南京师范大学文学院,江苏南京210097

出  处:《南京师范大学文学院学报》2013年第1期176-181,共6页Journal of School of Chinese Language and Culture Nanjing Normal University

基  金:国家社科基金重大招标项目"汉语史语料库建设研究"(编号:10&ZD117);江苏省高校哲学社会科学重点研究基地重大项目"先秦文献词汇知识挖掘"(编号:2010JDXM023);江苏高校优势学科建设工程资助项目;受到江苏省哲学社会科学基金项目(编号:10YYB007);江苏省普通高校研究生科研创新计划(编号:CXLX12_0357)的资金资助

摘  要:为了提高先秦文献词性标注的精确率,提出一种利用注疏文献的注音信息来进一步校正词性标注结果的方法。《春秋左传正义》中对破读字音有注释,且有较为规范的注音体例,在标注了《广韵》中多音字词性的基础上,通过比对注音,确定《左传》中某多音字的读音,进而确定词性。实验一共检查了词性标注精确率达90%的《左传》中1231个含多音字的句子,涉及到单音节词词型423个,正确校正了41个词型共92处错误。对古籍校勘及古籍信息处理有较高价值。In order to improve the accuracy in tagging the speech in pre - Qin texts, we suggest a method which is based on information provided by the phonetic notation in the comments of ancient texts to adjust the result of tagging. Chunqiu Zuozhuan Zhengyi has notes on unregularly pronunciation of words, and has its reg- ulated phonetic notation system. Based on tagging the speech of polyphonic words according to Guangyun, and by comparing the phonetic notations, the pronunciation of a polyphonic word in Zuozhuan can be determined, then its speech can be confirmed. The experiment has checked 1231 sentences in Zuozhuan, which contains polyphonic words and their speech tagging has reached an accuracy rate of 90%. 423 monosyllable words are involved, 92 errors in 4l word types have been correctly adjusted. The experiment is valuable to ancient text research and information processing.

关 键 词:《春秋左传正义》 词性标注 语言信息 

分 类 号:H109.2[语言文字—汉语]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象