检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:戴茹冰 侍冰清 李斌[1] 曲维光[1,2] DAI Ru-bing;SHI Bing-qing;LI Bin;QU Wei-guang(Nanjing Normal University, Nanjing Jiangsu 210097)
机构地区:[1]南京师范大学文学院,江苏南京210097 [2]南京师范大学计算机科学与技术学院,江苏南京210023
出 处:《汉语学习》2019年第5期45-53,共9页Chinese Language Learning
基 金:国家自然科学基金项目“汉语抽象意义表示关键技术研究”(项目编号:61772278);国家社会科学基金项目“中文抽象语义库的构建及自动分析研究”(项目编号:18BYY127)资助
摘 要:省略作为一种复杂的语言现象,一直是汉语语义研究的重要课题。如何将省略的语义内容补全以还原句子的完整语义也是机器理解自然语言的关键。本文基于AMR(Abstract Meaning Representation)语料统计得到含有语义省略信息的"的"字结构,针对特指性和泛指性省略类型,采用特殊句式核心谓词对应主宾语和基于谓词框架抽取核心谓词搭配必有论元成分的策略,确定补全的语义类别。研究结果表明,该方法对于省略"的"字结构中心语补全有较好的效果,可为自动理解深层语义奠定基础。Ellipsis as a complex language phenomenon has always been an important topic in Chinese semantic research. How to complete the omitted semantic content to restore the complete semantics of the sentence is also the key to the machine understanding natural language. Based on the statistics of AMR(Abstract Meaning Representation) corpus, this paper obtains the "de" construction with semantic ellipsis information and the model uses subject or object corresponding to the core predicate to determine the conceptual category of the ellipsis head for the "de" construction of the special sentence pattern. We extract the candidates with argument components from the core predicate of the "de" construction by using the predicate frame to determine the semantic concept type of the ellipsis. Experiment shows that this method has a good effect on head completion of "de" construction with semantic ellipsis and lays the foundation for automatic understanding of deep semantics.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229