システムを構築するにはどうすればよいですか?

import nltk
sentence = [('the','DT'),('little','JJ'),('yellow','JJ'),('dog','NN'),('brak','VBD')]
grammer = "NP: {<DT>?<JJ>*<NN>}"cp = nltk.RegexpParser(grammer) #生成规则result = cp.parse(sentence) #进行分块print(result)

result.draw() #调用matplotlib库画出来

import nltk
sentence = [('the','DT'),('little','JJ'),('yellow','JJ'),('dog','NN'),('bark','VBD'),('at','IN'),('the','DT'),('cat','NN')]
grammer = """NP:             {<DT>?<JJ>*<NN>}            }<VBD|NN>+{            """  #加缝隙，必须保存换行符cp = nltk.RegexpParser(grammer) #生成规则result = cp.parse(sentence) #进行分块print(result)

tree1 = nltk.Tree('NP',['Alick'])print(tree1)
tree2 = nltk.Tree('N',['Alick','Rabbit'])print(tree2)
tree3 = nltk.Tree('S',[tree1,tree2])print(tree3.label()) #查看树的结点tree3.draw()

#这段代码在python2下运行from nltk.corpus import conll2000print conll2000.chunked_sents('train.txt')[99] #查看已经分块的一个句子text = """   he /PRP/ B-NP   accepted /VBD/ B-VP   the DT B-NP   position NN I-NP   of IN B-PP   vice NN B-NP   chairman NN I-NP   of IN B-PP   Carlyle NNP B-NP   Group NNP I-NP   , , O   a DT B-NP   merchant NN I-NP   banking NN I-NP   concern NN I-NP   . . O"""result = nltk.chunk.conllstr2tree(text,chunk_types=['NP'])

class UnigramChunker(nltk.ChunkParserI):"""        一元分块器，        该分块器可以从训练句子集中找出每个词性标注最有可能的分块标记，        然后使用这些信息进行分块    """def __init__(self, train_sents):"""            构造函数            :param train_sents: Tree对象列表        """train_data = []for sent in train_sents:# 将Tree对象转换为IOB标记列表[(word, tag, IOB-tag), ...]conlltags = nltk.chunk.tree2conlltags(sent)# 找出每个词性标注对应的IOB标记ti_list = [(t, i) for w, t, i in conlltags]
            train_data.append(ti_list)# 使用一元标注器进行训练self.__tagger = nltk.UnigramTagger(train_data)def parse(self, tokens):"""            对句子进行分块            :param tokens: 标注词性的单词列表            :return: Tree对象        """# 取出词性标注tags = [tag for (word, tag) in tokens]# 对词性标注进行分块标记ti_list = self.__tagger.tag(tags)# 取出IOB标记iob_tags = [iob_tag for (tag, iob_tag) in ti_list]# 组合成conll标记conlltags = [(word, pos, iob_tag) for ((word, pos), iob_tag) in zip(tokens, iob_tags)]return nltk.chunk.conlltags2tree(conlltags)
test_sents = conll2000.chunked_sents("test.txt", chunk_types=["NP"])
train_sents = conll2000.chunked_sents("train.txt", chunk_types=["NP"])

unigram_chunker = UnigramChunker(train_sents)print(unigram_chunker.evaluate(test_sents))