当前位置:   article > 正文

LTP语义依赖关系说明

语义依赖关系

LTP语义依赖关系说明

中文语法分析是目前的自然语言处理的主要任务之一,语义依赖分析是目前实施中文语法分析的主要理论技术,开源的工具则主要有stanford parser和哈工大的语音云LTP

LTP语义依赖关系说明

附:LTP依存分析模块所使用的依存关系标记含义 (http://ir.hit.edu.cn/demo/ltp)
依存关系标记(共24个)
定中关系ATT(attribute)
数量关系QUN(quantity)
并列关系COO(coordinate)
同位关系APP(appositive)
前附加关系LAD(left adjunct)
后附加关系RAD(right adjunct)
动宾关系VOB(verb-object)
介宾关系POB(preposition-object)
主谓关系SBV(subject-verb)
比拟关系SIM(similarity)
核心HED(head)
连动结构VV(verb-verb)
关联结构CNJ(conjunctive)
语态结构MT(mood-tense)
独立结构IS(independent structure)
状中结构ADV(adverbial)
动补结构CMP(complement)
“的”字结构DE
“地”字结构DI
“得”字结构DEI
“把”字结构BA
“被”字结构BEI
独立分句IC(independent clause)
依存分句DC(dependent clause)

stanford语义依赖关系说明

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)

声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/小小林熬夜学编程/article/detail/348906
推荐阅读
相关标签
  

闽ICP备14008679号