中文基本复合名词短语语义关系体系及知识库构建
|
摘要
名词短语一直是中外语言学领域的重要研究对象,近年来在自然语言处理领域也受到了研究者的持续关注。英文方面,已建立了一定规模的名词短语语义关系知识库。但迄今为止,尚未建立相应或更大规模的描述名词短语语义关系的中文资源。该文借鉴国内外诸多学者对名词短语语义分类的研究成果,对大规模真实语料中的基本复合名词短语实例进行试标注与分析,建立了中文基本复合名词短语语义关系体系及相应句法语义知识库,该库能够为中文基本复合名词短语句法语义的研究提供基础数据资源。目前该库共含有18 281条高频基本复合名词短语,每条短语均标注了语义关系、短语结构及是否指称实体等信息,每条短语包含的两个名词还分别标注了语义类信息。语义类信息基于北京大学《现代汉语语义词典》。基于该知识库,该文还做了基本复合名词短语句法语义的初步统计与分析。
As an important linguistic issue,the noun compound has arouse close attention in the NLP community recently.In English,a relatively large-scale noun compound semantic relation knowledge base has been established.To establish the similar Chinese resources,this paper tries to tag and analyze the basic compound nouns in the largescale real corpus,and establishes the basic noun compound semantic relation hierarchy and the corresponding syntax and semantic knowledge base in Chinese.So far,the knowledge base contains 18 281 high-frequency basic noun compounds,each labeled with semantic relation,phrase structure and referential entity information.The two nouns in each noun compound are further annotated for the semantic category according to the SKCC of Peking University.Based on this knowledge base,we also provide preliminary statistics and analysis of syntactic and semantics of basic noun compounds.
As an important linguistic issue,the noun compound has arouse close attention in the NLP community recently.In English,a relatively large-scale noun compound semantic relation knowledge base has been established.To establish the similar Chinese resources,this paper tries to tag and analyze the basic compound nouns in the largescale real corpus,and establishes the basic noun compound semantic relation hierarchy and the corresponding syntax and semantic knowledge base in Chinese.So far,the knowledge base contains 18 281 high-frequency basic noun compounds,each labeled with semantic relation,phrase structure and referential entity information.The two nouns in each noun compound are further annotated for the semantic category according to the SKCC of Peking University.Based on this knowledge base,we also provide preliminary statistics and analysis of syntactic and semantics of basic noun compounds.
引文
[1]Downing P.On the creation and use of English compound nouns[J].Language,1977:810-842.
[2]吕叔湘.现代汉语语法提纲[M](油印本),1976.
[3]Vanderwende L.Algorithm for automatic interpretation of noun sequences[C]//Proceedings of the 15th Conference on Computational Linguistics:Volume 2.Association for Computational Linguistics,1994:782-788.
[4]Vanderwende L.SENS:The system for evaluating noun sequences[M].Natural language processing:The PLNLP approach.Springer US,1993:161-173.
[5]Tratz S,Hovy E.A taxonomy,dataset,and classifier for automatic noun compound interpretation[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2010:678-687.
[6]魏雪,袁毓林.基于规则的汉语名名组合的自动释义研究[J].中文信息学报,2014,28(3):1-10.
[7]魏雪,袁毓林.基于语义类和物性角色建构名名组合的释义模板[J].世界汉语教学,2013(2):172-181.
[8]Levi J N.On the alleged idiosyncrasy of non-predicate NP’s[C].Chicago Linguistic Society.1974(10):402-15.
[9]Levi J N.The syntax and semantics of complex nominals[M].Academic Press,1978.
[10]Warren B.Semantic patterns of noun-noun compounds[M].Gothenburg:Gothenburg University Press.1978.
[11]Barker K,Szpakowicz S.Semi-automatic recognition of noun modifier relationships[C]//Proc.of the 17th International Conference on Computational Linguistics,1998.
[12]Nastase V,Szpakowicz S.Exploring nounmodifier semantic relations[C]//Proc.of the 5th International Workshop on Computational Semantics,2003.
[13]Girju R.Improving the interpretation of noun phrases with cross-linguistic information[C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics(ACL 2007),2007.
[14]óSéaghdha D,Copestake A.Co-occurrence contexts for noun compound interpretation[C]//Proceedings of ACL-07Workshop Broader Perspective Multiword Expressions,Prague,Czech Republic,2007.
[15]朱德熙.语法讲义[M].北京:商务印书馆,1982.
[16]袁毓林.谓词隐含及其句法后果---“的”字结构的称代规则和“的”的语法、语义功能[J].中国语文,1995(04):241-255.
[17]张卫国,梁社会.定语类型和槽关系类型的对应及其对名词语义分析的作用[C]//全国计算语言学联合学术会议,2003.
[18]李宇明.非谓形容词的词类地位[J].中国语文,1996(01):1-9.
[19]文贞惠.“N_1(的)N_2”偏正结构中N_1与N_2之间语义关系的鉴定[J].语文研究,1999(03):22-27.
[20]蔺璜.定语位置上名词的句法表现及其语义特征[J].山西大学学报(哲学社会科学版),2005,28(2):95-99.
[21]谭景春.名名偏正结构的语义关系及其在词典释义中的作用[J].中国语文,2010(04):342-355,384.
[22]黄国营.“的”字的句法、语义功能[J].语言研究,1982(01):101-129.
[23]孔令达.“名_1+的+名_2”结构中心名词省略的语义规则[J].安徽师大学报(哲学社会科学版),1992(01):103-107.
[24]单强,牛守祯.定语的语义类型举要[J].潍坊教育学院学报,1999(04):27-30.
[25]马洪海.“名+名”组合的语义考察[J].信阳师范学院学报(哲学社会科学版),1999(01):117-120.
[26]周日安.名名组合的句法语义研究[D].广州:暨南大学博士学位论文,2007.
[27]魏雪.面向语义搜索的汉语名名组合的自动释义研究[D].北京:北京大学硕士学位论文,2012.
[28]鲁川.智能计算机的知识表示和汉语的语义研究[J].语文建设,1992(11):30-33.
[29]林杏光,张庆旭.现代汉语槽关系研究[J].汉语学习,1998(6):7-10.
[30]冯志伟.中文信息MMT模型[J].语言文字应用,1992(04):21-30.
[31]董振东,董强,郝长伶.知网的理论发现[J].中文信息学报,2007,21(04):3-9.
[32]刘开瑛.汉语框架语义知识库构建工程[A]//中文信息处理前沿进展---中国中文信息学会二十五周年学术会议论文集[C].中国中文信息学会,2006:8.
[33]B Rosario,M Hearst.Classifying the semantic relations in noun compounds via a domain-Specific lexical hierarchy[C]//Proceedings of Conf.of Empirical Methods Natural Language Process.,Somerset,NJ,USA,2001:82-90.
[34]Kim S N,Baldwin T.Automatic interpretation of compound nouns using WordNet:Similarity[C]//Proceedings of 2nd International Joint Conf.on Natural Language Processing,2005.
[35]卢涌.面向深层语义表示的“名词+的+名词”结构语义释义研究[D].北京:北京语言大学硕士学位论文,2017.
(1)复合名词短语源于英语研究者所用“Noun Compounds”,意为多个名词复合而成的短语,整体表现类似一个名词。本文将该结构的名词个数限定为2,这样的结构是复合名词短语中最“基本”的一类,因此加上“基本”,对复合名词短语做词数限制。以下简称“NN短语”。
(1)该库已经开源,共享在:https://github.com/liupengyuan/Basic-Noun-Compounds
(1)类似“x月y日”的短语,由于分词原因,本文没有统计在内。
[2]吕叔湘.现代汉语语法提纲[M](油印本),1976.
[3]Vanderwende L.Algorithm for automatic interpretation of noun sequences[C]//Proceedings of the 15th Conference on Computational Linguistics:Volume 2.Association for Computational Linguistics,1994:782-788.
[4]Vanderwende L.SENS:The system for evaluating noun sequences[M].Natural language processing:The PLNLP approach.Springer US,1993:161-173.
[5]Tratz S,Hovy E.A taxonomy,dataset,and classifier for automatic noun compound interpretation[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2010:678-687.
[6]魏雪,袁毓林.基于规则的汉语名名组合的自动释义研究[J].中文信息学报,2014,28(3):1-10.
[7]魏雪,袁毓林.基于语义类和物性角色建构名名组合的释义模板[J].世界汉语教学,2013(2):172-181.
[8]Levi J N.On the alleged idiosyncrasy of non-predicate NP’s[C].Chicago Linguistic Society.1974(10):402-15.
[9]Levi J N.The syntax and semantics of complex nominals[M].Academic Press,1978.
[10]Warren B.Semantic patterns of noun-noun compounds[M].Gothenburg:Gothenburg University Press.1978.
[11]Barker K,Szpakowicz S.Semi-automatic recognition of noun modifier relationships[C]//Proc.of the 17th International Conference on Computational Linguistics,1998.
[12]Nastase V,Szpakowicz S.Exploring nounmodifier semantic relations[C]//Proc.of the 5th International Workshop on Computational Semantics,2003.
[13]Girju R.Improving the interpretation of noun phrases with cross-linguistic information[C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics(ACL 2007),2007.
[14]óSéaghdha D,Copestake A.Co-occurrence contexts for noun compound interpretation[C]//Proceedings of ACL-07Workshop Broader Perspective Multiword Expressions,Prague,Czech Republic,2007.
[15]朱德熙.语法讲义[M].北京:商务印书馆,1982.
[16]袁毓林.谓词隐含及其句法后果---“的”字结构的称代规则和“的”的语法、语义功能[J].中国语文,1995(04):241-255.
[17]张卫国,梁社会.定语类型和槽关系类型的对应及其对名词语义分析的作用[C]//全国计算语言学联合学术会议,2003.
[18]李宇明.非谓形容词的词类地位[J].中国语文,1996(01):1-9.
[19]文贞惠.“N_1(的)N_2”偏正结构中N_1与N_2之间语义关系的鉴定[J].语文研究,1999(03):22-27.
[20]蔺璜.定语位置上名词的句法表现及其语义特征[J].山西大学学报(哲学社会科学版),2005,28(2):95-99.
[21]谭景春.名名偏正结构的语义关系及其在词典释义中的作用[J].中国语文,2010(04):342-355,384.
[22]黄国营.“的”字的句法、语义功能[J].语言研究,1982(01):101-129.
[23]孔令达.“名_1+的+名_2”结构中心名词省略的语义规则[J].安徽师大学报(哲学社会科学版),1992(01):103-107.
[24]单强,牛守祯.定语的语义类型举要[J].潍坊教育学院学报,1999(04):27-30.
[25]马洪海.“名+名”组合的语义考察[J].信阳师范学院学报(哲学社会科学版),1999(01):117-120.
[26]周日安.名名组合的句法语义研究[D].广州:暨南大学博士学位论文,2007.
[27]魏雪.面向语义搜索的汉语名名组合的自动释义研究[D].北京:北京大学硕士学位论文,2012.
[28]鲁川.智能计算机的知识表示和汉语的语义研究[J].语文建设,1992(11):30-33.
[29]林杏光,张庆旭.现代汉语槽关系研究[J].汉语学习,1998(6):7-10.
[30]冯志伟.中文信息MMT模型[J].语言文字应用,1992(04):21-30.
[31]董振东,董强,郝长伶.知网的理论发现[J].中文信息学报,2007,21(04):3-9.
[32]刘开瑛.汉语框架语义知识库构建工程[A]//中文信息处理前沿进展---中国中文信息学会二十五周年学术会议论文集[C].中国中文信息学会,2006:8.
[33]B Rosario,M Hearst.Classifying the semantic relations in noun compounds via a domain-Specific lexical hierarchy[C]//Proceedings of Conf.of Empirical Methods Natural Language Process.,Somerset,NJ,USA,2001:82-90.
[34]Kim S N,Baldwin T.Automatic interpretation of compound nouns using WordNet:Similarity[C]//Proceedings of 2nd International Joint Conf.on Natural Language Processing,2005.
[35]卢涌.面向深层语义表示的“名词+的+名词”结构语义释义研究[D].北京:北京语言大学硕士学位论文,2017.
(1)复合名词短语源于英语研究者所用“Noun Compounds”,意为多个名词复合而成的短语,整体表现类似一个名词。本文将该结构的名词个数限定为2,这样的结构是复合名词短语中最“基本”的一类,因此加上“基本”,对复合名词短语做词数限制。以下简称“NN短语”。
(1)该库已经开源,共享在:https://github.com/liupengyuan/Basic-Noun-Compounds
(1)类似“x月y日”的短语,由于分词原因,本文没有统计在内。