- c - 在位数组中找到第一个零
- linux - Unix 显示有关匹配两种模式之一的文件的信息
- 正则表达式替换多个文件
- linux - 隐藏来自 xtrace 的命令
我最近致力于使用 nltk 从文本中提取关系。所以我构建了一个示例文本:“Tom is the cofounder of Microsoft.”并使用以下程序进行测试并且不返回任何内容。我不明白为什么。
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()
"Gates was born in Seattle, Washington on October 28, 1955. "
(S (PERSON Gates/NNS) was/VBD born/VBN in/IN (GPE Seattle/NNP) ,/, (GPE Washington/NNP) on/IN October/NNP 28/CD ,/, 1955/CD ./.)
[PER: 'Gates/NNS'] 'was/VBD born/VBN in/IN' [GPE: 'Seattle/NNP']
"Gates was born in Seattle on October 28, 1955. "
test() 不返回任何内容。
输出是由函数引起的:semi_rel2reldict(pairs, window=5, trace=False),只有当len(pairs) > 2时才返回结果,这就是为什么当一个句子少于三个NE时会返回None。
这是错误还是我以错误的方式使用了 NLTK?
最佳答案
首先,用 ne_chunk
分块 NE,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').
"""
当你调用这个函数时:
extract_rels('PER', 'GPE', sent, corpus='ace', pattern=OF, window=10)
它依次执行 4 个过程。
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)
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你的输入语句 Tom is the cofounder of Microsoft
,tree2semi_rel()
返回什么:
>>> 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')])]]
因此它返回一个包含 2 个列表的列表,第一个内部列表由一个空白列表和包含“PERSON”标签的 Tree
组成。
[[], Tree('PERSON', [('Tom', 'NNP')])]
第二个列表由短语 is the cofounder of
和包含“ORGANIZATION”的 Tree
组成。
让我们继续。
extract_rel
然后尝试将这些对更改为某种关系字典reldicts = semi_rel2reldict(pairs)
如果我们查看 semi_rel2reldict
函数返回的示例语句,我们会发现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
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
semi_rel2reldict()
做的第一件事是检查 tree2semi_rel()
的输出中有超过 2 个元素的地方,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 extract_rel
没有返回任何内容的原因。
现在的问题是如何让 extract_rel()
返回一些东西,即使是来自 tree2semi_rel()
的 2 个元素? 这甚至可能吗?
让我们试试不同的句子:
>>> 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'})]
但这只能证实当 tree2semi_rel
返回成对的 <2 时 extract_rel
无法提取。如果我们删除 while 的条件会发生什么len(对) > 2
?
为什么我们不能while len(pairs) > 1
?
如果我们仔细观察代码,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 pairs
的第三个元素,如果 pairs
的长度为 2,您将得到一个 IndexError
.
那么,如果我们删除 rcon
键并将其简单地更改为 while len(pairs) >= 2
会发生什么?
为此,我们必须覆盖 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 extract_rels()
中还有第 4 步。
pattern
参数的正则表达式执行 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)
现在让我们用破解版的 semi_rel2reldict
试试看:
>>> 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'})]
有效!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']
关于python - NLTK 关系提取不返回任何内容,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/40480839/
我正在做一个业余爱好项目,使用 Ruby、PHP 或 Java 来抓取 ASP.net 网站的内容。例如,如果网站 url“www.myaspnet.com/home.aspx”。我想从 home.a
如果我有这些字符串: mystrings <- c("X2/D2/F4", "X10/D9/F4", "X3/D22/F4",
我有以下数据集 > head(names$SAMPLE_ID) [1] "Bacteria|Proteobacteria|Gammaproteobacteria|Pseudomonadales|Mor
设置: 3个域类A,B和C。A和B在插件中。 C在依赖于此插件的应用程序中。 class A{ B b static mapping = { b fetch: 'joi
我不知道如何提取 XML 文件中的开始标记元素名称。我很接近〜意味着没有错误,我正在获取标签名称,但我正在获取标签名称加上信息。我得到的是: {http://www.publishing.org}au
我有一个字符串 x <- "Name of the Student? Michael Sneider" 我想从中提取“Michael Sneider”。 我用过: str_extract_all(x,
我有一个如下所示的文本文件: [* content I want *] [ more content ] 我想读取该文件并能够提取我想要的内容。我能做的最好的事情如下,但它会返回 [更多内容] 请注意
假设我有一个项目集合 $collection = array( 'item1' => array( 'post' => $post, 'ca
我正在寻找一种过滤文本文件的方法。我有许多文件夹名称,其中包含许多文本文件,文本文件有几个没有人员,每个人员有 10 个群集/组(我在这里只显示了 3 个)。但是每个组/簇可能包含几个原语(我在这里展
我已经编写了一个从某个网页中提取网址的代码,我面临的问题是它不会以网页上相同的方式提取网址,我的意思是如果该网址位于某些网页中法语,它不会按原样提取它。我该如何解决这个问题? import reque
如何在 C# 中提取 ZipFile?(ZipFile 是包含文件和目录) 最佳答案 为此使用工具。类似于 SharpZip .据我所知 - .NET 不支持开箱即用的 ZIP 文件。 来自 here
我有一个表达: [training_width]:lofmimics 我要提取[]之间的内容,在上面的例子中我要 training_width 我试过以下方法: QRegularExpression
我正在尝试创建一个 Bash 脚本,该脚本将从命令行给出的最后一个参数提取到一个变量中以供其他地方使用。这是我正在处理的脚本: #!/bin/bash # compact - archive and
我正在寻找一个 JavaScript 函数/正则表达式来从 URI 中提取 *.com...(在客户端完成) 它应该适用于以下情况: siphone.com = siphone.com qwr.sip
关闭。这个问题需要更多focused .它目前不接受答案。 想改进这个问题吗? 更新问题,使其只关注一个问题 editing this post . 关闭 8 年前。 Improve this qu
编辑:添加了实际的 JSON 对象和代码以供审查 我有这种格式的 JSON(只是这种层次结构,假设 JSON 正常工作) {u'kind': u'calendar#events', u'default
我已经编写了代码来使用 BeautifulSoup 提取一本书的 url 和标题来自页面。 但它并没有在 > 之间提取惊人的 super 科学故事 1930 年 4 月这本书的名字。和 标签。 如何提
使用 Java,我想提取美元符号 $ 之间的单词。 例如: String = " this is first attribute $color$. this is the second attribu
您好,我正在尝试找到一种方法来确定字符串中的常量,然后提取该常量左侧的一定数量的字符。 例如-我有一个 .txt 文件,在那个文件的某处有数字 00nnn 数字的例子是 00234 00765 ...
php读取zip文件(删除文件,提取文件,增加文件)实例 从zip压缩文件中提取文件 复制代码 代码如下: <?php /* php 从zip压缩文件
我是一名优秀的程序员,十分优秀!