我最近正致力于使用nltk从文本中提取关系。所以我建立了一个示例文本：“汤姆是微软的联合创始人。”并使用以下程序测试并返回任何内容。我无法弄清楚为什么。
我使用的是NLTK版本：3.2.1，python版本：3.5.2。
这是我的代码：
import re
import nltk
from nltk.sem.relextract import extract_rels, rtuple
from nltk.tokenize import sent_tokenize, word_tokenize
def test():
with open('sample.txt', 'r') as f:
sample = f.read() # "Tom is the cofounder of Microsoft"
sentences = sent_tokenize(sample)
tokenized_sentences = [word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.tag.pos_tag(sentence) for sentence in tokenized_sentences]
OF = re.compile(r'.*\bof\b.*')
for i, sent in enumerate(tagged_sentences):
sent = nltk.chunk.ne_chunk(sent) # ne_chunk method expects one tagged sentence
rels = extract_rels('PER', 'GPE', sent, corpus='ace', pattern=OF, window=10)
for rel in rels:
print('{0:<5}{1}'.format(i, rtuple(rel)))
if __name__ == '__main__':
test()
“盖茨于1955年10月28日出生在华盛顿州西雅图。”
（S（PERSON Gates / NNS）/ / VBD出生/ VBN in / IN（GPE Seattle / NNP），/，（GPE Washington / NNP）/ IN 10月/ NNP 28 / CD，/，1955 / CD ./。 ）
[PER：'盖茨/ NNS']'/ VBD出生/ VBN in / IN'[GPE：'Seattle / NNP']
“盖茨于1955年10月28日出生在西雅图。”
test（）什么都不返回。
输出是由函数引起的：semi_rel2reldict（pairs，window = 5，trace = False），仅当len（pairs）> 2时才返回结果，这就是为什么当一个少于三个NE的句子将返回None时。
这是一个错误还是我错误地使用了NLTK？
首先，对于使用ne_chunk的网格块，这个成语看起来像这样
>>> from nltk import ne_chunk, pos_tag, word_tokenize
>>> text = "Tom is the cofounder of Microsoft"
>>> chunked = ne_chunk(pos_tag(word_tokenize(text)))
>>> chunked
Tree('S', [Tree('PERSON', [('Tom', 'NNP')]), ('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN'), Tree('ORGANIZATION', [('Microsoft', 'NNP')])])
（另见https://stackoverflow.com/a/31838373/610569）
接下来让我们来看看extract_rels function。
def extract_rels(subjclass, objclass, doc, corpus='ace', pattern=None, window=10):
"""
Filter the output of ``semi_rel2reldict`` according to specified NE classes and a filler pattern.
The parameters ``subjclass`` and ``objclass`` can be used to restrict the
Named Entities to particular types (any of 'LOCATION', 'ORGANIZATION',
'PERSON', 'DURATION', 'DATE', 'CARDINAL', 'PERCENT', 'MONEY', 'MEASURE').
"""
当你唤起这个功能时：
extract_rels('PER', 'GPE', sent, corpus='ace', pattern=OF, window=10)
它按顺序执行4个过程。
subjclass and objclassare valid即yaazkssvpoi：
https://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L202
if subjclass and subjclass not in NE_CLASSES[corpus]:
if _expand(subjclass) in NE_CLASSES[corpus]:
subjclass = _expand(subjclass)
else:
raise ValueError("your value for the subject type has not been recognized: %s" % subjclass)
if objclass and objclass not in NE_CLASSES[corpus]:
if _expand(objclass) in NE_CLASSES[corpus]:
objclass = _expand(objclass)
else:
raise ValueError("your value for the object type has not been recognized: %s" % objclass)
现在让我们看看你的输入句子if corpus == 'ace' or corpus == 'conll2002':
pairs = tree2semi_rel(doc)
elif corpus == 'ieer':
pairs = tree2semi_rel(doc.text) + tree2semi_rel(doc.headline)
else:
raise ValueError("corpus type not recognized")
，Tom is the cofounder of Microsoft返回什么：
tree2semi_rel()因此它返回一个包含2个列表的列表，第一个内部列表包含空白列表，>>> from nltk.sem.relextract import tree2semi_rel, semi_rel2reldict
>>> from nltk import word_tokenize, pos_tag, ne_chunk
>>> text = "Tom is the cofounder of Microsoft"
>>> chunked = ne_chunk(pos_tag(word_tokenize(text)))
>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
包含“PERSON”标记。
Tree第二个列表包含短语[[], Tree('PERSON', [('Tom', 'NNP')])]
和包含“ORGANIZATION”的is the cofounder of。
让我们继续。
Tree then tries to change the pairs to some sort of relation dictionaryextract_rel如果我们查看reldicts = semi_rel2reldict(pairs)
函数返回的示例句子，我们会看到这是空列表返回的位置：
semi_rel2reldict那么让我们看看>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
>>> semi_rel2reldict(tree2semi_rel(chunked))
[]
semi_rel2reldict的代码：
https://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L144
def semi_rel2reldict(pairs, window=5, trace=False):
"""
Converts the pairs generated by ``tree2semi_rel`` into a 'reldict': a dictionary which
stores information about the subject and object NEs plus the filler between them.
Additionally, a left and right context of length =< window are captured (within
a given input sentence).
:param pairs: a pair of list(str) and ``Tree``, as generated by
:param window: a threshold for the number of items to include in the left and right context
:type window: int
:return: 'relation' dictionaries whose keys are 'lcon', 'subjclass', 'subjtext', 'subjsym', 'filler', objclass', objtext', 'objsym' and 'rcon'
:rtype: list(defaultdict)
"""
result = []
while len(pairs) > 2:
reldict = defaultdict(str)
reldict['lcon'] = _join(pairs[0][0][-window:])
reldict['subjclass'] = pairs[0][1].label()
reldict['subjtext'] = _join(pairs[0][1].leaves())
reldict['subjsym'] = list2sym(pairs[0][1].leaves())
reldict['filler'] = _join(pairs[1][0])
reldict['untagged_filler'] = _join(pairs[1][0], untag=True)
reldict['objclass'] = pairs[1][1].label()
reldict['objtext'] = _join(pairs[1][1].leaves())
reldict['objsym'] = list2sym(pairs[1][1].leaves())
reldict['rcon'] = _join(pairs[2][0][:window])
if trace:
print("(%s(%s, %s)" % (reldict['untagged_filler'], reldict['subjclass'], reldict['objclass']))
result.append(reldict)
pairs = pairs[1:]
return result
做的第一件事是检查来自semi_rel2reldict()的输出超过2个元素的位置，你的例句不是：
tree2semi_rel()啊哈，这就是为什么>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
>>> len(tree2semi_rel(chunked))
2
>>> len(tree2semi_rel(chunked)) > 2
False
什么也没回来。
现在问题是如何让extract_rel返回一些东西，即使是来自extract_rel()的2个元素？这甚至可能吗？
让我们尝试一个不同的句子：
tree2semi_rel()但这只能证实当>>> text = "Tom is the cofounder of Microsoft and now he is the founder of Marcohard"
>>> chunked = ne_chunk(pos_tag(word_tokenize(text)))
>>> chunked
Tree('S', [Tree('PERSON', [('Tom', 'NNP')]), ('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN'), Tree('ORGANIZATION', [('Microsoft', 'NNP')]), ('and', 'CC'), ('now', 'RB'), ('he', 'PRP'), ('is', 'VBZ'), ('the', 'DT'), ('founder', 'NN'), ('of', 'IN'), Tree('PERSON', [('Marcohard', 'NNP')])])
>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])], [[('and', 'CC'), ('now', 'RB'), ('he', 'PRP'), ('is', 'VBZ'), ('the', 'DT'), ('founder', 'NN'), ('of', 'IN')], Tree('PERSON', [('Marcohard', 'NNP')])]]
>>> len(tree2semi_rel(chunked)) > 2
True
>>> semi_rel2reldict(tree2semi_rel(chunked))
[defaultdict(<type 'str'>, {'lcon': '', 'untagged_filler': 'is the cofounder of', 'filler': 'is/VBZ the/DT cofounder/NN of/IN', 'objsym': 'microsoft', 'objclass': 'ORGANIZATION', 'objtext': 'Microsoft/NNP', 'subjsym': 'tom', 'subjclass': 'PERSON', 'rcon': 'and/CC now/RB he/PRP is/VBZ the/DT', 'subjtext': 'Tom/NNP'})]
返回<2对时，extract_rel无法提取。如果我们删除tree2semi_rel的条件会怎样？
为什么我们不能做while len(pairs) > 2？
如果我们仔细研究代码，我们会看到填充reldict的最后一行，while len(pairs) > 1：
https://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L169
它试图访问reldict['rcon'] = _join(pairs[2][0][:window])
的第3个元素，如果pairs的长度是2，你将得到一个pairs。
那么如果我们删除那个IndexError密钥并简单地将其更改为rcon会发生什么？
要做到这一点，我们必须覆盖while len(pairs) >= 2函数：
semi_rel2redict()啊!它有效，但在>>> from nltk.sem.relextract import _join, list2sym
>>> from collections import defaultdict
>>> def semi_rel2reldict(pairs, window=5, trace=False):
... """
... Converts the pairs generated by ``tree2semi_rel`` into a 'reldict': a dictionary which
... stores information about the subject and object NEs plus the filler between them.
... Additionally, a left and right context of length =< window are captured (within
... a given input sentence).
... :param pairs: a pair of list(str) and ``Tree``, as generated by
... :param window: a threshold for the number of items to include in the left and right context
... :type window: int
... :return: 'relation' dictionaries whose keys are 'lcon', 'subjclass', 'subjtext', 'subjsym', 'filler', objclass', objtext', 'objsym' and 'rcon'
... :rtype: list(defaultdict)
... """
... result = []
... while len(pairs) >= 2:
... reldict = defaultdict(str)
... reldict['lcon'] = _join(pairs[0][0][-window:])
... reldict['subjclass'] = pairs[0][1].label()
... reldict['subjtext'] = _join(pairs[0][1].leaves())
... reldict['subjsym'] = list2sym(pairs[0][1].leaves())
... reldict['filler'] = _join(pairs[1][0])
... reldict['untagged_filler'] = _join(pairs[1][0], untag=True)
... reldict['objclass'] = pairs[1][1].label()
... reldict['objtext'] = _join(pairs[1][1].leaves())
... reldict['objsym'] = list2sym(pairs[1][1].leaves())
... reldict['rcon'] = []
... if trace:
... print("(%s(%s, %s)" % (reldict['untagged_filler'], reldict['subjclass'], reldict['objclass']))
... result.append(reldict)
... pairs = pairs[1:]
... return result
...
>>> text = "Tom is the cofounder of Microsoft"
>>> chunked = ne_chunk(pos_tag(word_tokenize(text)))
>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
>>> semi_rel2reldict(tree2semi_rel(chunked))
[defaultdict(<type 'str'>, {'lcon': '', 'untagged_filler': 'is the cofounder of', 'filler': 'is/VBZ the/DT cofounder/NN of/IN', 'objsym': 'microsoft', 'objclass': 'ORGANIZATION', 'objtext': 'Microsoft/NNP', 'subjsym': 'tom', 'subjclass': 'PERSON', 'rcon': [], 'subjtext': 'Tom/NNP'})]
仍然是第四步。
extract_rels() parameter, pattern:https://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L222
现在让我们尝试使用被攻击的relfilter = lambda x: (x['subjclass'] == subjclass and
len(x['filler'].split()) <= window and
pattern.match(x['filler']) and
x['objclass'] == objclass)
版本：
semi_rel2reldict有用！现在让我们以元组形式看到它：
>>> text = "Tom is the cofounder of Microsoft"
>>> chunked = ne_chunk(pos_tag(word_tokenize(text)))
>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
>>> semi_rel2reldict(tree2semi_rel(chunked))
[defaultdict(<type 'str'>, {'lcon': '', 'untagged_filler': 'is the cofounder of', 'filler': 'is/VBZ the/DT cofounder/NN of/IN', 'objsym': 'microsoft', 'objclass': 'ORGANIZATION', 'objtext': 'Microsoft/NNP', 'subjsym': 'tom', 'subjclass': 'PERSON', 'rcon': [], 'subjtext': 'Tom/NNP'})]
>>>
>>> pattern = re.compile(r'.*\bof\b.*')
>>> reldicts = semi_rel2reldict(tree2semi_rel(chunked))
>>> relfilter = lambda x: (x['subjclass'] == subjclass and
... len(x['filler'].split()) <= window and
... pattern.match(x['filler']) and
... x['objclass'] == objclass)
>>> relfilter
<function <lambda> at 0x112e591b8>
>>> subjclass = 'PERSON'
>>> objclass = 'ORGANIZATION'
>>> window = 5
>>> list(filter(relfilter, reldicts))
[defaultdict(<type 'str'>, {'lcon': '', 'untagged_filler': 'is the cofounder of', 'filler': 'is/VBZ the/DT cofounder/NN of/IN', 'objsym': 'microsoft', 'objclass': 'ORGANIZATION', 'objtext': 'Microsoft/NNP', 'subjsym': 'tom', 'subjclass': 'PERSON', 'rcon': [], 'subjtext': 'Tom/NNP'})]
alvas的解决方案效果非常好！虽然稍作修改：而不是写作
>>> from nltk.sem.relextract import rtuple
>>> rels = list(filter(relfilter, reldicts))
>>> for rel in rels:
... print rtuple(rel)
...
[PER: 'Tom/NNP'] 'is/VBZ the/DT cofounder/NN of/IN' [ORG: 'Microsoft/NNP']
请用
>>> for rel in rels:
... print rtuple(rel)
- 无法添加评论