Python 如何在NLTK中连续使用不同的分块器？

我使用“Python3文本处理与NLTK3食谱”来分析文本。 我创建了两个chunker“LocationChunker”和“PersonChunker”，它们工作得很好

我到处找，但你怎么能同时用这两个词来分析一个句子呢？之后我还想使用ne_chunk函数

使用Postagger非常容易声明回退，但如何使用ChunkParserI实现这一点

---

非常感谢。

以下代码是我根据您提到的示例制作的简单地名录

# -*- coding: utf-8 -*-
import codecs
from lxml.html.builder import DT
import os
import re

from nltk.chunk.util import conlltags2tree
from nltk.chunk import ChunkParserI
from nltk.tag import pos_tag
from nltk.tokenize import wordpunct_tokenize


def sub_leaves(tree, node):
    return [t.leaves() for t in tree.subtrees(lambda s: s.node == node)]


class Gazetteer(ChunkParserI):
    """
    Find and annotate a list of words that matches patterns.
    Patterns may be regular expressions in the form list of tuples.
    Every tuple has the regular expression and the iob tag for this one.
    Before applying gazetteer words a part of speech tagging should
    be performed. So, you have to pass your tagger as a parameter.
    Example:
        >>> patterns = [(u"Αθήνα[ς]?", "LOC"), (u"Νομική[ς]? [Σσ]χολή[ς]?", "ORG")]
        >>> gazetteer = Gazetteer(patterns, nltk.pos_tag, nltk.wordpunct_tokenize)
        >>> text = u"Η Νομική σχολή της Αθήνας"
        >>> t = gazetteer.parse(text)
        >>> print(unicode(t))
        ... (S Η/DT (ORG Νομική/NN σχολή/NN) της/DT (LOC Αθήνας/NN))
    """

    def __init__(self, patterns, pos_tagger, tokenizer):
        """
        Initialize the class.

        :param patterns:
            The patterns to search in text is a list of tuples with regular
            expression and the tag to apply
        :param pos_tagger:
            The tagger to use for applying part of speech to the text
        :param tokenizer:
            The tokenizer to use for tokenizing the text
        """
        self.patterns = patterns
        self.pos_tag = pos_tagger
        self.tokenize = tokenizer
        self.lookahead = 0  # how many words it is possible to be a gazetteer word
        self.words = []  # Keep the words found by applying the regular expressions
        self.iobtags = []  # For each set of words keep the coresponding tag

    def iob_tags(self, tagged_sent):
        """
        Search the tagged sentences for gazetteer words and apply their iob tags.

        :param tagged_sent:
            A tokenized text with part of speech tags
        :type tagged_sent: list
        :return:
            yields the IOB tag of the word with it's character, eg. B-LOCATION
        :rtype:
        """
        i = 0
        l = len(tagged_sent)
        inside = False  # marks the I- tag
        iobs = []

        while i < l:
            word, pos_tag = tagged_sent[i]
            j = i + 1  # the next word
            k = j + self.lookahead  # how many words in a row we may search
            nextwords, nexttags = [], []  # for now, just the ith word
            add_tag = False  # no tag, this is O

            while j <= k:
                words = ' '.join([word] + nextwords)  # expand our word list
                if words in self.words:  # search for words
                    index = self.words.index(words)  # keep index to use for iob tags
                    if inside:
                        iobs.append((word, pos_tag, 'I-' + self.iobtags[index]))  # use the index tag
                    else:
                        iobs.append((word, pos_tag, 'B-' + self.iobtags[index]))

                    for nword, ntag in zip(nextwords, nexttags):  # there was more than one word
                        iobs.append((nword, ntag, 'I-' + self.iobtags[index]))  # apply I- tag to all of them

                    add_tag, inside = True, True
                    i = j  # skip tagged words
                    break

                if j < l:  # we haven't reach the length of tagged sentences
                    nextword, nexttag = tagged_sent[j]  # get next word and it's tag
                    nextwords.append(nextword)
                    nexttags.append(nexttag)
                    j += 1
                else:
                    break

            if not add_tag:  # unkown words
                inside = False
                i += 1
                iobs.append((word, pos_tag, 'O'))  # it's an Outsider

        return iobs

    def parse(self, text, conlltags=True):
        """
        Given a text, applies tokenization, part of speech tagging and the
        gazetteer words with their tags. Returns an conll tree.

        :param text: The text to parse
        :type text: str
        :param conlltags:
        :type conlltags:
        :return: An conll tree
        :rtype:
        """
        # apply the regular expressions and find all the
        # gazetteer words in text
        for pattern, tag in self.patterns:
            words_found = set(re.findall(pattern, text))  # keep the unique words
            if len(words_found) > 0:
                for word in words_found:  # words_found may be more than one
                    self.words.append(word)  # keep the words
                    self.iobtags.append(tag)  # and their tag

        # find the pattern with the maximum words.
        # this will be the look ahead variable
        for word in self.words:  # don't care about tags now
            nwords = word.count(' ')
            if nwords > self.lookahead:
                self.lookahead = nwords

        # tokenize and apply part of speech tagging
        tagged_sent = self.pos_tag(self.tokenize(text))
        # find the iob tags
        iobs = self.iob_tags(tagged_sent)

        if conlltags:
            return conlltags2tree(iobs)
        else:
            return iobs


if __name__ == "__main__":
    patterns = [(u"Αθήνα[ς]?", "LOC"), (u"Νομική[ς]? [Σσ]χολή[ς]?", "ORG")]
    g = Gazetteer(patterns, pos_tag, wordpunct_tokenize)
    text = u"Η Νομική σχολή της Αθήνας"
    t = g.parse(text)
    print(unicode(t))


    dir_with_lists = "Lists"
    patterns = []
    tags = []
    for root, dirs, files in os.walk(dir_with_lists):
        for f in files:
            lines = codecs.open(os.path.join(root, f), 'r', 'utf-8').readlines()
            tag = os.path.splitext(f)[0]
            for l in lines[1:]:
                patterns.append((l.rstrip(), tag))
                tags.append(tag)

    text = codecs.open("sample.txt", 'r', "utf-8").read()
    #g = Gazetteer(patterns)
    t = g.parse(text.lower())
    print unicode(t)

    for tag in set(tags):
        for gaz_word in sub_leaves(t, tag):
            print gaz_word[0][0], tag

#-*-编码：utf-8-*-
导入编解码器
从lxml.html.builder导入DT
导入操作系统
进口稀土
从nltk.chunk.util导入conlltags2tree
从nltk.chunk导入ChunkParserI
从nltk.tag导入pos_标记
从nltk.tokenize导入wordpunct\u tokenize
def sub_叶（树、节点）：
在tree.subtrees中为t返回[t.leaves（）（lambda s:s.node==node）]
类别地名录（CHUNKPASSERI）：
"""
查找并注释与模式匹配的单词列表。
模式可以是元组列表形式的正则表达式。
每个元组都有正则表达式和这个元组的iob标记。
在使用地名索引词之前，应先进行词性标注
因此，必须将标记器作为参数传递。
例子：
>>>模式=[（u“θθνα[ς]？”，“LOC”），（u“μοκ[ς]？[σ]χολ[ς]？，“ORG”）]
>>>地名索引=地名索引（模式、nltk.pos_标记、nltk.wordputt_标记化）
>>>text=u“ΗΝομικήσχολήτηςΑθήνας”
>>>t=地名索引。解析（文本）
>>>打印（unicode（t））
…（SΗ/DT（ORGΝμοκή/NNσχολή/NN）της/DT（LOCΑθήνας/NN））
"""
定义初始化（自我、模式、位置标记器、标记器）：
"""
初始化该类。
：参数模式：
要在文本中搜索的模式是一个具有正则表达式的元组列表
表达式和要应用的标记
：参数位置标记器：
用于将词性应用于文本的标记器
：参数标记器：
用于标记文本的标记器
"""
self.patterns=模式
self.pos\u tag=pos\u tagger
self.tokenize=tokenizer
self.lookahead=0#有多少个单词可能是地名录中的单词
self.words=[]#保留通过应用正则表达式找到的单词
self.iobtags=[]#对于每组单词，保留相应的标记
def iob_标记（自标记、已发送标记）：
"""
在标记的句子中搜索地名索引词并应用它们的iob标记。
：参数已发送：
带有词性标记的标记化文本
：类型已发送：列表
：返回：
生成单词的IOB标签及其字符，例如B-LOCATION
：rtype:
"""
i=0
l=len（已标记且已发送）
inside=False#标记I标记
iobs=[]
而我

在

中，如果uuuu name_uuuuuuu==“uuuuu main_uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu

在后面的代码中，我从名为
列表的目录中读取文件（将其放在上面代码所在的文件夹中）。每个文件的名称都成为地名索引的标签。所以，制作像
LOC.txt
这样的文件，其中包含位置模式（
LOC
tag）、
PERSON.txt
个人模式等等。
怎么样？我已经阅读了该网页，其中没有解决我问题的方法。