NLP之Stanford Parser using NLTK

因为官网的使用的很不方便，各个参数没有详细的说明，也查不到很好的资料了。所以决定使用python配合NLTK来获取Constituency Parser和Denpendency Parser。

一、安装python

操作系统win10
jdk（版本1.8.0_151）
anaconda（版本4.4.0），python（版本3.6.1）
略

二、安装NLTK

pip install nltk

安装完成之后进入python命令中，输入

import nltk
nltk.download()

如图所示：

然后就会弹出一个框，具体我目前也不是很懂，大概就是提供的一些资源包，所以我就全部先download
如图所示：

这样就完成了。

三、stanford parser与NLTK

在不设置classpath的情况下，简单实用stanford parser的几个简单的demo

1.Constituency Parser

# -*- coding: utf-8 -*-
import os
from nltk.parse.stanford import StanfordParser

os.environ['STANFORD_PARSER'] = './model/stanford-parser.jar'
os.environ['STANFORD_MODELS'] = './model/stanford-parser-3.8.0-models.jar'

parser = StanfordParser(model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz")
sentences = parser.raw_parse("the quick brown fox jumps over the \" lazy \" dog .")
# for line in sentences:
#     for t in line:
#         print(t)

# GUI
for line in sentences:
    for sentence in line:
        sentence.draw()

2.Denpendency Parser

# -*- coding: utf-8 -*-
import os
from nltk.parse.stanford import StanfordDependencyParser

os.environ['STANFORD_PARSER'] = './model/stanford-parser.jar'
os.environ['STANFORD_MODELS'] = './model/stanford-parser-3.8.0-models.jar'

parser = StanfordDependencyParser(model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz")
sentences = parser.raw_parse("the quick brown fox jumps over the lazy dog")
# 返回的是tree
# for line in sentences:
#     print(line)

res = list(parser.parse("the quick brown fox jumps over the lazy dog .".split()))
for row in res[0].triples():
    print(row)

---

这是分割线

---

最终版的：

# -*- coding: utf-8 -*-

import os
from nltk.parse.stanford import StanfordDependencyParser

os.environ['STANFORD_PARSER'] = './model/stanford-parser.jar'
os.environ['STANFORD_MODELS'] = './model/stanford-parser-3.8.0-models.jar'

parser = StanfordDependencyParser(model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz")

fin = open("./data/raw.clean.test", encoding="utf-8")
fout = open("./result/test.txt", "w+", encoding="utf-8")

i = 0
for line in fin.readlines():
    if line is None or line == "":
        pass
    else:
        sentences, = parser.parse(line.split("|||")[0].split(" "))
        # print(sentences.to_conll(4))
        fout.write(sentences.to_conll(4))
        fout.write('\n')
        fout.flush()
    i += 1
    print(i)

fin.close()
fout.close()

最终的样子非常符合我的需求

over