自然语言处理：基于PCFG的中文句法分析样例

秒速五厘米 2023-05-29 06:22 72阅读 0赞

### 1、下载 ###

[https://nlp.stanford.edu/software/lex-parser.shtml\#Download][https_nlp.stanford.edu_software_lex-parser.shtml_Download]

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70]  
解压缩  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 1]  
复制stanford-parser.jar和stanford-parser-3.9.2-models.jar到python程序文件同目录下  
![在这里插入图片描述][20191105091902879.png]

### 2、python程序 ###

#coding=utf-8
    
    # 分词
    import jieba
    
    # PCFG句法分析
    from nltk.parse import stanford
    import os
    
    if __name__ == '__main__':
    
        string = '我准备坐地铁去虹桥火车站接你。'
        seg_list = jieba.cut(string, cut_all=False, HMM=True)
        seg_str = ' '.join(seg_list)
    
        print(seg_str)
        root = './'
        parser_path = root + 'stanford-parser.jar'
        model_path =  root + 'stanford-parser-3.9.2-models.jar'
    
        # 指定JDK路径
        if not os.environ.get('JAVA_HOME'):
            JAVA_HOME = '/usr/lib/jvm/jdk1.8'
            os.environ['JAVA_HOME'] = JAVA_HOME
    
        # PCFG模型路径
        pcfg_path = 'edu/stanford/nlp/models/lexparser/chinesePCFG.ser.gz'
    
        parser = stanford.StanfordParser(
            path_to_jar=parser_path,
            path_to_models_jar=model_path,
            model_path=pcfg_path
        )
    
        sentence = parser.raw_parse(seg_str)
        for line in sentence:
            print(line.leaves())
            line.draw()

输出

runfile('D:/Users/chengyq/py/chapter-6/PCFG.py', wdir='D:/Users/chengyq/py/chapter-6')
    我 准备 坐地铁 去 虹桥 火车站 接 你 。
    D:/Users/chengyq/py/chapter-6/PCFG.py:32: DeprecationWarning: The StanfordParser will be deprecated
    Please use nltk.parse.corenlp.CoreNLPParser instead.
      model_path=pcfg_path
    ['我', '准备', '坐地铁', '去', '虹桥', '火车站', '接', '你', '。']

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 2]

[https_nlp.stanford.edu_software_lex-parser.shtml_Download]: https://nlp.stanford.edu/software/lex-parser.shtml#Download
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20191105091837907.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20191105091942543.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw==,size_16,color_FFFFFF,t_70
[20191105091902879.png]: https://img-blog.csdnimg.cn/20191105091902879.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20191105092452784.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5neXVxaWFuZw==,size_16,color_FFFFFF,t_70