分块器评估与语言结构中的递归

       声明：代码的运行环境为Python3。Python3与Python2在一些细节上会有所不同，希望广大读者注意。本博客以代码为主，代码中会有详细的注释。相关文章将会发布在我的个人博客专栏《Python自然语言处理》，欢迎大家关注。

---

一、信息提取与分块

1、信息提取 

# 信息提取
def ie_preprocess(document):
    sentences = nltk.sent_tokenize(document)
    sentences = [nltk.word_tokenize(sent) for sent in sentences]
    sentences = [nltk.pos_tag(sent) for sent in sentences]  # 词性标注

2、分块

# 正则表达式分块
grammar = r"""
NP: {<DT|PP\$>?<JJ>*<NN>} # chunk determiner/possessive, adjectives and nouns
{<NNP>+} # chunk sequences of proper nouns
"""  # 定义分块的语法
cp = nltk.RegexpParser(grammar)  # 定义分块器
sentence = [("Rapunzel", "NNP"), ("let", "VBD"), ("down", "RP"),
            ("her", "PP$"), ("long", "JJ"), ("golden", "JJ"), ("hair", "NN")]
result = cp.parse(sentence)  # 将分块器应用于已有的句子中
print(result)  # 打印结果
result.draw()  # 树状结构表示出来

       分块之后的结果及树状表示如下所示：

(S
  (NP Rapunzel/NNP)
  let/VBD
  down/RP
  (NP her/PP$ long/JJ golden/JJ hair/NN))

3、例子

# 探索文本语料库
cp = nltk.RegexpParser('CHUNK: {<V.*> <TO> <V.*>}')
brown = nltk.corpus.brown
for sent in brown.tagged_sents():
    tree = cp.parse(sent)
    for subtree in tree.subtrees():
        if subtree.label() == 'CHUNK': print(subtree)

# 加缝隙
grammar = r"""
NP:
{<.*>+} # Chunk everything
}<VBD|IN>+{ # Chink sequences of VBD and IN
"""
sentence = [("the", "DT"), ("little", "JJ"), ("yellow", "JJ"),
            ("dog", "NN"), ("barked", "VBD"), ("at", "IN"), ("the", "DT"), ("cat", "NN")]
cp = nltk.RegexpParser(grammar)
print(cp.parse(sentence))

二、评估分块器

1、评估基准

from nltk.corpus import conll2000

cp = nltk.RegexpParser("")
test_sents = conll2000.chunked_sents('test.txt', chunk_types=['NP'])
print(cp.evaluate(test_sents))

       当RegexpParser为空是，可以得到评估的结果为：

ChunkParse score:
    IOB Accuracy:  43.4%%
    Precision:      0.0%%
    Recall:         0.0%%
    F-Measure:      0.0%%

2、简单评估

grammar = r"NP: {<[CDJNP].*>+}"
cp = nltk.RegexpParser(grammar)
print(cp.evaluate(test_sents))

       此时的评估结果为：

ChunkParse score:
    IOB Accuracy:  87.7%%
    Precision:     70.6%%
    Recall:        67.8%%
    F-Measure:     69.2%%

3、使用unigram标注器对名词短语分块

# 使用unigram标注器对名词短语分块
class UnigramChunker(nltk.ChunkParserI):
    def __init__(self, train_sents):
        train_data = [[(t, c) for w, t, c in nltk.chunk.tree2conlltags(sent)]
                      for sent in train_sents]
        self.tagger = nltk.UnigramTagger(train_data)

    def parse(self, sentence):
        pos_tags = [pos for (word, pos) in sentence]
        tagged_pos_tags = self.tagger.tag(pos_tags)
        chunktags = [chunktag for (pos, chunktag) in tagged_pos_tags]
        conlltags = [(word, pos, chunktag) for ((word, pos), chunktag)
                     in zip(sentence, chunktags)]
        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))

       得到的结果为：

ChunkParse score:
    IOB Accuracy:  92.9%%
    Precision:     79.9%%
    Recall:        86.8%%
    F-Measure:     83.2%%

4、使用Bigram标注器分块

class BigramChunker(nltk.ChunkParserI):
    def __init__(self, train_sents):
        train_data = [[(t, c) for w, t, c in nltk.chunk.tree2conlltags(sent)]
                      for sent in train_sents]
        self.tagger = nltk.BigramTagger(train_data)

    def parse(self, sentence):
        pos_tags = [pos for (word, pos) in sentence]
        tagged_pos_tags = self.tagger.tag(pos_tags)
        chunktags = [chunktag for (pos, chunktag) in tagged_pos_tags]
        conlltags = [(word, pos, chunktag) for ((word, pos), chunktag)
                     in zip(sentence, chunktags)]
        return nltk.chunk.conlltags2tree(conlltags)


bigram_chunker = BigramChunker(train_sents)
print(bigram_chunker.evaluate(test_sents))

       得到的结果为：

ChunkParse score:
    IOB Accuracy:  93.3%%
    Precision:     82.3%%
    Recall:        86.8%%
    F-Measure:     84.5%%

5、训练基于分类器的分块器

（1）

# 训练基于分类器的分块器
class ConsecutiveNPChunkTagger(nltk.TaggerI):
    def __init__(self, train_sents):
        train_set = []
        for tagged_sent in train_sents:
            untagged_sent = nltk.tag.untag(tagged_sent)
            history = []
            for i, (word, tag) in enumerate(tagged_sent):
                featureset = npchunk_features(untagged_sent, i, history)
                train_set.append((featureset, tag))
                history.append(tag)
        self.classifier = nltk.MaxentClassifier.train(train_set, trace=0)  # 使用最大熵分类器（此处使用此分类器比使用朴素贝叶斯分类器效果好）

    def tag(self, sentence):
        history = []
        for i, word in enumerate(sentence):
            featureset = npchunk_features(sentence, i, history)
            tag = self.classifier.classify(featureset)
            history.append(tag)
        return zip(sentence, history)


class ConsecutiveNPChunker(nltk.ChunkParserI):
    def __init__(self, train_sents):
        tagged_sents = [[((w, t), c) for (w, t, c) in nltk.chunk.tree2conlltags(sent)]
                        for sent in train_sents]
        self.tagger = ConsecutiveNPChunkTagger(tagged_sents)

    def parse(self, sentence):
        tagged_sents = self.tagger.tag(sentence)
        conlltags = [(w, t, c) for ((w, t), c) in tagged_sents]
        return nltk.chunk.conlltags2tree(conlltags)


def npchunk_features(sentence, i, history):
    word, pos = sentence[i]
    return {"pos": pos}


chunker = ConsecutiveNPChunker(train_sents)
print(chunker.evaluate(test_sents))

（2）

def npchunk_features(sentence, i, history):
    word, pos = sentence[i]
    if i == 0:
        prevword, prevpos = "<START>", "<START>"
    else:
        prevword, prevpos = sentence[i - 1]
    return {"pos": pos, "prevpos": prevpos}


chunker = ConsecutiveNPChunker(train_sents)
print(chunker.evaluate(test_sents))

（3）

def npchunk_features(sentence, i, history):
    word, pos = sentence[i]
    if i == 0:
        prevword, prevpos = "<START>", "<START>"
    else:
        prevword, prevpos = sentence[i - 1]
    return {"pos": pos, "word": word, "prevpos": prevpos}


chunker = ConsecutiveNPChunker(train_sents)
print(chunker.evaluate(test_sents))

（4）

def npchunk_features(sentence, i, history):
    word, pos = sentence[i]
    if i == 0:
        prevword, prevpos = "<START>", "<START>"
    else:
        prevword, prevpos = sentence[i - 1]
    if i == len(sentence) - 1:
        nextword, nextpos = "<END>", "<END>"
    else:
        nextword, nextpos = sentence[i + 1]
    return {"pos": pos,
            "word": word,
            "prevpos": prevpos,
            "nextpos": nextpos,
            "prevpos+pos": "%s+%s" % (prevpos, pos),
            "pos+nextpos": "%s+%s" % (pos, nextpos),
            "tags-since-dt": tags_since_dt(sentence, i)}


def tags_since_dt(sentence, i):
    tags = set()
    for word, pos in sentence[:i]:
        if pos == 'DT':
            tags = set()
        else:
            tags.add(pos)
        return '+'.join(sorted(tags))


chunker = ConsecutiveNPChunker(train_sents)
print(chunker.evaluate(test_sents))

三、语言结构中的递归

1、用级联分块器构建嵌套结构

# 用级联分块器构建嵌套结构
grammar = r"""
NP: {<DT|JJ|NN.*>+} # Chunk sequences of DT, JJ, NN
PP: {<IN><NP>} # Chunk prepositions followed by NP
VP: {<VB.*><NP|PP|CLAUSE>+$} # Chunk verbs and their arguments
CLAUSE: {<NP><VP>} # Chunk NP, VP
"""
cp = nltk.RegexpParser(grammar)
sentence = [("Mary", "NN"), ("saw", "VBD"), ("the", "DT"), ("cat", "NN"),
            ("sit", "VB"), ("on", "IN"), ("the", "DT"), ("mat", "NN")]
print(cp.parse(sentence))

结果为：

(S
  (NP Mary/NN)
  saw/VBD
  (CLAUSE
    (NP the/DT cat/NN)
    (VP sit/VB (PP on/IN (NP the/DT mat/NN)))))

再次测试：

cp = nltk.RegexpParser(grammar, loop=2)
print(cp.parse(sentence))

结果为：

(S
  (CLAUSE
    (NP Mary/NN)
    (VP
      saw/VBD
      (CLAUSE
        (NP the/DT cat/NN)
        (VP sit/VB (PP on/IN (NP the/DT mat/NN)))))))

2、树与遍历

（1）树 

tree1 = nltk.Tree('NP', ['Alice'])
tree2 = nltk.Tree('NP', ['the', 'rabbit'])
tree3 = nltk.Tree('VP', ['chased', tree2])
tree4 = nltk.Tree('S', [tree1, tree3])
print(tree4)

结果为：

(S (NP Alice) (VP chased (NP the rabbit)))

（2）遍历

# 遍历树
def traverse(t):
    try:
        t.label()
    except AttributeError:
        print(t),
    else:
        # Now we know that t.node is defined
        print('(', t.label(),)
        for child in t:
            traverse(child)
        print(')',)

traverse(tree4)

结果：

( S
( NP
Alice
)
( VP
chased
( NP
the
rabbit
)
)
)

3、关系抽取

import re

IN = re.compile(r'.*\bin\b(?!\b.+ing)')
for doc in nltk.corpus.ieer.parsed_docs('NYT_19980315'):
    for rel in nltk.sem.extract_rels('ORG', 'LOC', doc, corpus='ieer', pattern=IN):
        print(nltk.sem.relextract.rtuple(rel))

from nltk.corpus import conll2002

vnv = """
(
is/V| # 3rd sing present and
was/V| # past forms of the verb zijn ('be')
werd/V| # and also present
wordt/V # past of worden ('become')
)
.* # followed by anything
van/Prep # followed by van ('of')
"""
VAN = re.compile(vnv, re.VERBOSE)
for doc in conll2002.chunked_sents('ned.train'):
    for r in nltk.sem.extract_rels('PER', 'ORG', doc, corpus='conll2002', pattern=VAN):
        print(nltk.sem.relextract.rtuple(r))