python中使用NLTK中的stanford parser进行句法分析

[Amina_L]

我在网络上搜到用nltk同样可以使用stanford parser，代码如下：

import itertools
#import nltk
from nltk.tokenize import StanfordSegmenter
from nltk.tokenize import StanfordTokenizer
from nltk.tag import StanfordPOSTagger
from nltk.parse.stanford import StanfordParser
from nltk.parse import stanford
from nltk.tag.api import TaggerI
parser = StanfordParser(
    path_to_jar='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser.jar',
    path_to_models_jar='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser-3.6.0-models.jar',
    model_path='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser-3.6.0-models\\edu\\stanford\\nlp\\models\\lexparser\\englishPCFG.ser.gz')
#parser = StanfordParser('C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser.jar','C:\\ProgramData\\Anaconda3\\stanfordparser\\slf4j-api.jar','C:\\ProgramData\\Anaconda3\\stanfordparser\\data\\english-onesent.txt')
lt = parser.parse("the quick brown fox jumps over the lazy dog".split())
print(list(lt))

但是问题出现了

import itertools#import nltkfrom nltk.tokenize import StanfordSegmenterfrom nltk.tokenize import StanfordTokenizerfrom nltk.tag import StanfordPOSTaggerfrom nltk.parse.stanford import StanfordParserfrom nltk.parse import stanfordparser = StanfordParser( path_to_jar='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser.jar', path_to_models_jar='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser-3.6.0-models.jar', model_path='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser-3.6.0-models\\edu\\stanford\\nlp\\models\\lexparser\\englishPCFG.ser.gz')#parser = StanfordParser('C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser.jar','C:\\ProgramData\\Anaconda3\\stanfordparser\\slf4j-api.jar','C:\\ProgramData\\Anaconda3\\stanfordparser\\data\\english-onesent.txt')lt = parser.parse("the quick brown fox jumps over the lazy dog".split())from nltk.tag.api import TaggerIprint(list(lt))


\
第 1 个(共 60 个)


\\

问题
输出
调试控制台
终端
Traceback (most recent call last):
File "g:\chromedownload\textrank-master\new.py", line 12, in <module>
model_path='C:\\ProgramData\\Anaconda3\\stanfordparser\\stanford-parser-3.6.0-models\\edu\\stanford\\nlp\\models\\lexparser\\englishPCFG.ser.gz')
File "C:\ProgramData\Anaconda3\lib\site-packages\nltk\parse\stanford.py", line 51, in __init__
key=lambda model_name: re.match(self._JAR, model_name)
TypeError: '>' not supported between instances of 'NoneType' and 'NoneType'
这个是什么原因？看出错的函数定义是

    def __init__(self, path_to_jar=None, path_to_models_jar=None,
                 model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
                 encoding='utf8', verbose=False,
                 java_options='-mx1000m', corenlp_options=''):

        # find the most recent code and model jar
        stanford_jar = max(
            find_jar_iter(
                self._JAR, path_to_jar,
                env_vars=('STANFORD_PARSER', 'STANFORD_CORENLP'),
                searchpath=(), url=_stanford_url,
                verbose=verbose, is_regex=True
            ),
            key=lambda model_name: re.match(self._JAR, model_name)
        )

请问该如何解决这个问题？