转载Stanford CoreNLP Typed Dependencies

Posted tatarget

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了转载Stanford CoreNLP Typed Dependencies相关的知识,希望对你有一定的参考价值。

总结自Stanford typed dependencies manual

原文链接:http://www.jianshu.com/p/5c461cf096c4

依存关系描述句子中词与词之间的各种语法关系。一句句子可以表示成如下的依存关系树。

Bell, based in Los Angeles, makes and distributes electronic, computer and building products.

技术分享

CoreNLP中的依存关系有50来种(都是二元的关系),下面总结:

    • 1. acomp: adjectival complement
      用于动词的形容词补语。
      动词-->形容词
      “She looks very beautiful.” acomp(looks,beautiful)

    • 2. advcl: adverbial clause modifier
      修饰动词的状语从句。
      主句中的动词-->从句中的主要成分
      “The accident happened as the night was falling” advcl(happened, falling)

    • 3. advmod: adverb modifier 
      (非从句)的副词。
      被修饰者-->副词
      “Genetically modified food” advmod(modified, genetically)

    • 4. agent: agent
      用于补充过去时态的动词,通常跟着介词“by”。
      过去时态的动词-->补充的名词
      “The man has been killed by the police” agent(killed, police)

    • 5. amod: adjectival modifier
      修饰名词短语的形容修饰语。
      名词短语-->形容修饰语
      “Sam eats red meat” amod(meat, red)

    • 6. appos: appostional modifier
      修饰名词短语的名词短语(通常紧挨着)
      被修饰的名词短语-->名词短语
      “Bill ( John ’s cousin ) ” appos(Bill, cousin)

    • 7. aux: auxiliary
      助动词
      动词-->助动词
      “Reagan has died ”aux(died, has)

    • 8. auxpass: passive auxiliary
      过去式的助动词
      动词-->过去式的助动词
      “Kennedy has been killed” auxpass(killed, been)

    • 9. cc: coordination
      第一个并列词--> 协同关系词
      “Bill is big and honest” cc(big, and)

    • 10. ccomp: clausal complement
      被补充说明的词-->补语从句的主要成分(决定语义的词)
      “He says that you like to swim” ccomp(says, like)

    • 11. conj: conjunct
      用协同连词(and、or)连接的两个元素
      第一个元素-->第二个元素
      “Bill is big and honest” conj(big, honest)

    • 12. cop: copula
      系动词
      表语-->系动词
      “Bill is big” cop(big, is)

    • 13. csubj: clausual subject
      主语从句
      谓语动词-->主语从句中的主要成分
      “What she said makes sense” csubj(makes, said)

    • 14. csubjpass: clausal passive subject
      主从被动关系
      谓语动词(被动)-->主语从句中的主要成分
      “That she lied was suspected by everyone” csubjpass(suspected, lied)

    • 15. dep: dependent
      系统无法识别的依赖关系
      “Then, as if to show that he could, . . . ” dep(show, if)

    • 16. det: determiner
      限定词
      名词短语-->限定词
      “The man is here” det(man, the)

    • 17. discourse: discourse element
      句子主要部分-->感叹词、语气词
      "Iguazu is in Argentina :) " discourse(is, :))

    • 18. dobj: direct object
      动词(给予)-->直接宾语
      “She gave me a raise” dobj(gave, raise)

    • 19. expl: expletive
      从句的主要动词-->there
      “There is a ghost in the room” expl(is, There)

    • 20. goeswith: goes with
      两个本来应该连在一起的词
      第二部分-->第一部分
      They come here with out legal permission gosewith(out, with)

    • 21. iobj: indirect object
      动词(给予)-->间接宾语
      “She gave me a raise” iobj(gave, me)

    • 22. mark: marker
      从句的主要成分-->从句修饰的主体(标记语)
      ”He says that you like to swim“ marker(swim,that)

    • 23. mwe: multi-word expression
      固定搭配
      “I like dogs as well as cats” mwe(well, as)

    • 24. neg: negation modifier
      否定修饰
      被修饰词-->否定词
      “Bill is not a scientist” neg(scientist, not)

    • 25. nn: noun compound modifier
      名词合成修饰
      “Oil price futures” nn(futures, oil) nn(futures, price)

    • 26. npadvmod: noun phrase as adverbial modifier
      名词短语作为副词修饰
      副词修饰的词-->名词
      “The director is 65 years old” npadvmod(old, years)

    • 27. nsubj: nominal subject
      名词性主语
      句子的主要成分(一般是动词)-->主语
      “Clinton defeated Dole” nsubj(defeated, Clinton)

    • 28. nsubjpass: passive nominal subject
      被动的名词主语
      句子的主要成分-->主语(被动)
      “Dole was defeated by Clinton” nsubjpass(defeated, Dole)

    • 29. num: numeric modifier
      数词
      名词-->数量
      “Sam ate 3 sheep” num(sheep, 3)

    • 30. number: element of compound number
      复合形式的数词
      “I have four thousand sheep” number(thousand, four)

    • 31. parataxis: parataxis
      并列
      主要动词-->并列句的主要成分
      “The guy, John said, left early in the morning” parataxis(left, said)

    • 32. pcomp: prepositional complement
      介词的补语
      介词-->从句的主要成分
      “We have no information on whether users are at risk” pcomp(on, are)

    • 33. pobj: object of a preposition
      介词的宾语
      介词-->宾语
      “I sat on the chair” pobj(on, chair)

    • 34. poss: possession modifier
      所属修饰
      拥有者-->拥有物品
      “their offices” poss(offices, their)

    • 35. possessive: possessive modifier
      所属修饰
      拥有者-->‘s
      “Bill’s clothes” possessive(Bill, ’s)

    • 36. preconj: preconjunct
      名词短语的前部-->连词前面出现的词(both、either、neither)
      “Both the boys and the girls are here” preconj(boys, both)

    • 37. predet: predeterminer
      名词短语的前部-->在限定词前面出现的词
      “All the boys are here” predet(boys, all)

    • 38. prep: prepositional modifier
      介词修饰
      名词-->介词
      “I saw a cat in a hat” prep(cat, in)

    • 39. prepc: prepositional clausal modifier
      介词从句修饰
      主句主要词-->从句主要词
      “He purchased it without paying a premium” prepc without(purchased, paying)

    • 40. prt: phrasal verb particle
      动词短语
      “They shut down the station” prt(shut, down)

    • 41. punct: punctuation
      标点
      “Go home!” punct(Go, !)

    • 42. quantmod: quantifier phrase modifier
      数量短语
      数量-->数量修饰
      “About 200 people came to the party” quantmod(200, About)

    • 43. rcmod: relative clause modifier
      关系从句修饰
      名词短语的第一个词-->关系动词的主要词
      “I saw the man you love” rcmod(man, love)

    • 44. ref: referent
      指代关系
      被指代词-->指代词
      “I saw the book which you bought” ref (book, which)

    • 45. root: root
      根节点
      “I love French fries.” root(ROOT, love)

    • 46. tmod: temporal modifier
      时间修饰
      句子主要词(通常是动词)-->时间词
      “Last night, I swam in the pool” tmod(swam, night)

    • 47. vmod: reduced non-finite verbal modifier
      非谓语动词(to do)修饰
      修饰对象-->非谓语动词
      “Points to establish are . . . ” vmod(points, establish)

    • 48. xcomp: open clausal complement
      开放从句(缺少主语的从句)补语
      开放从句的补足对象(动词)-->开放从句的动词
      “He says that you like to swim” xcomp(like, swim)

    • 49. xsubj: controlling subject
      开放从句的动词-->实际控制对象(名词)
      “Tom likes to eat fish” xsubj(eat, Tom)




































































































































以上是关于转载Stanford CoreNLP Typed Dependencies的主要内容,如果未能解决你的问题,请参考以下文章

运行 Stanford.NLP.CoreNLP 示例时出现 TypeInitializationException

使用Stanford CoreNLP进行句法分析实战

Stanford Corenlp学习笔记——词性标注

开源中文分词工具探析:Stanford CoreNLP

stanford coreNLP CRFClassifier 模型加载和序列化

斯坦福 stanford coreNLP 中的PCFG parser-lexparser