首先，用 来分块 NE ne_chunk，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）
接下来我们看一下extract_rels函数。
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').
"""
当您调用此功能时：
extract_rels('PER', 'GPE', sent, corpus='ace', pattern=OF, window=10)
它依次执行 4 个过程。
1.它检查你的subjclass和objclass是否有效
即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)
2. 它从您的 NE 标记输入中提取“对”：
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")
现在让我们看看给定您的输入语句Tom is the cofounder of Microsoft，返回什么tree2semi_rel()：
>>> 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')])]]
所以它返回一个包含 2 个列表的列表，第一个内部列表由一个空白列表和Tree包含“PERSON”标签的列表组成。
[[], Tree('PERSON', [('Tom', 'NNP')])]
第二个列表由短语is the cofounder of和Tree包含“组织”的 组成。
让我们继续前进。
3.extract_rel然后尝试将对更改为某种关系字典
reldicts = semi_rel2reldict(pairs)
如果我们semi_rel2reldict用您的例句查看函数返回的内容，我们会看到这是空列表返回的地方：
>>> tree2semi_rel(chunked)
[[[], Tree('PERSON', [('Tom', 'NNP')])], [[('is', 'VBZ'), ('the', 'DT'), ('cofounder', 'NN'), ('of', 'IN')], Tree('ORGANIZATION', [('Microsoft', 'NNP')])]]
>>> semi_rel2reldict(tree2semi_rel(chunked))
[]
那么让我们看看semi_rel2reldict https://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L144的代码：
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
要做的第一件事semi_rel2reldict()是检查输出的位置有超过 2 个元素tree2semi_rel()，而您的例句没有：
>>> 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
啊哈，这就是为什么 theextract_rel什么都不返回。
现在出现的问题是，extract_rel()即使有 2 个元素，如何从 ? 中返回一些东西tree2semi_rel()？这甚至可能吗？
让我们尝试一个不同的句子：
>>> 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'})]
但这只能确认extract_rel当返回 < 2 对时无法提取tree2semi_rel。如果我们删除 的条件会发生什么while len(pairs) > 2？
为什么我们做不到while len(pairs) > 1？
如果我们仔细查看代码，我们会看到填充 reldict 的最后一行，https ://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L169 ：
reldict['rcon'] = _join(pairs[2][0][:window])
它尝试访问 的第三个元素，pairs如果 的长度pairs为 2，您将得到一个IndexError.
那么，如果我们删除该rcon键并简单地将其更改为 会发生什么while len(pairs) >= 2？
为此，我们必须重写该semi_rel2redict()函数：
>>> 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'})]
啊! 它有效，但仍有第四步extract_rels()。
pattern4. 给定您提供给参数的正则表达式，它执行 reldict 过滤器， https ://github.com/nltk/nltk/blob/develop/nltk/sem/relextract.py#L222 ：
relfilter = lambda x: (x['subjclass'] == subjclass and
len(x['filler'].split()) <= window and
pattern.match(x['filler']) and
x['objclass'] == objclass)
现在让我们试试破解版semi_rel2reldict：
>>> 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'})]
有用！现在让我们以元组形式查看它：
>>> 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']