成分句法分析与依存句法分析
2017-11-22 08:51
204 查看
转载http://blog.csdn.net/flybirp07/article/details/44834853
转载http://blog.csdn.net/u014422406/article/details/53954530
句法分析 parse
成分句法分析 constituency parse 把句子组织成短语的形式
依存句法分析 dependency parse 揭示了句子中词的依赖关系
依存句法树能够根据成分句法树转换而来,但成分句法树不能通过依存树转化来。转换的规则是head-finding rules from Zhang and Clark 2008
A constituency parse tree breaks a text into sub-phrases. Non-terminals in the tree are types of phrases, the terminals are the words in the sentence, and the edges are unlabeled. For a simple sentence "John sees Bill", a constituency parse would be:
句子 >> 短语
Sentence
|
+-------------+------------+
| |
Noun Phrase Verb Phrase
| |
John +-------+--------+
| |
Verb Noun Phrase
| |
sees Bill
A dependency parse connects words according to their relationships. Each vertex in the tree represents a word, child nodes are words that are dependent on the parent, and edges are labeled by the relationship. A dependency parse of "John sees Bill", would be:
句子 >> 关系(a, b)
sees
|
+--------------+
subject | | object
| |
John Bill
You should use the parser type that gets you closest to your goal. If you are interested in sub-phrases within the sentence, you probably want the constituency parse. If you are interested in the dependency relationships between words, then you probably want
the dependency parse.
The Stanford parser can give you either. In fact, the way it really works is to always parse the sentence with the constituency parser, and then, if needed, it performs a deterministic (rule-based) transformation on the constituency parse tree to convert it
into a dependency tree.
More can be found here:
http://en.wikipedia.org/wiki/Phrase_structure_grammar http://en.wikipedia.org/wiki/Dependency_grammar
转载http://blog.csdn.net/u014422406/article/details/53954530
句法分析 parse
成分句法分析 constituency parse 把句子组织成短语的形式
依存句法分析 dependency parse 揭示了句子中词的依赖关系
依存句法树能够根据成分句法树转换而来,但成分句法树不能通过依存树转化来。转换的规则是head-finding rules from Zhang and Clark 2008
A constituency parse tree breaks a text into sub-phrases. Non-terminals in the tree are types of phrases, the terminals are the words in the sentence, and the edges are unlabeled. For a simple sentence "John sees Bill", a constituency parse would be:
句子 >> 短语
Sentence
|
+-------------+------------+
| |
Noun Phrase Verb Phrase
| |
John +-------+--------+
| |
Verb Noun Phrase
| |
sees Bill
A dependency parse connects words according to their relationships. Each vertex in the tree represents a word, child nodes are words that are dependent on the parent, and edges are labeled by the relationship. A dependency parse of "John sees Bill", would be:
句子 >> 关系(a, b)
sees
|
+--------------+
subject | | object
| |
John Bill
You should use the parser type that gets you closest to your goal. If you are interested in sub-phrases within the sentence, you probably want the constituency parse. If you are interested in the dependency relationships between words, then you probably want
the dependency parse.
The Stanford parser can give you either. In fact, the way it really works is to always parse the sentence with the constituency parser, and then, if needed, it performs a deterministic (rule-based) transformation on the constituency parse tree to convert it
into a dependency tree.
More can be found here:
http://en.wikipedia.org/wiki/Phrase_structure_grammar http://en.wikipedia.org/wiki/Dependency_grammar
相关文章推荐
- Stanford3.8.0依存句法分析在java中运行
- 几何文本的依存句法分析
- 中文依存句法分析概述及应用
- 十二、教你如何利用强大的中文语言技术平台做依存句法和语义依存分析
- fudannlp - 开源中文自然语言处理工具包|中文分词|词性标注|依存句法分析|指代消解 - Google Project Hosting
- 依存句法分析与语义依存分析的区别
- 依存句法分析
- 中文依存句法分析
- 【已解决】win10环境下基于nltk搭建stanford parser环境,进行中文依存句法分析
- 数据驱动的依存句法分析方法简介(一)
- 中文依存句法分析概述及应用
- 使用Stanford CoreNLP的Python封装包处理中文(分词、词性标注、命名实体识别、句法树、依存句法分析)
- Dependency Parsing 依存句法分析
- 使用opennlp进行依存句法分析
- 依存句法分析与语义依存分析的区别
- 【已解决】win10环境下基于nltk搭建stanford parser环境,进行中文依存句法分析
- 基于神经网络的依存句法分析
- 中文依存句法分析概述及应用
- 依存句法分析与语义依存分析的区别--转载
- 依存句法分析与语义依存分析的区别