Python 用前面提到的人替换人称代词（喧闹的coref）

我想做一个嘈杂的解析，这样在给出一个个人的prounoun时，这个代词会被前一个（最近的）人替换掉

例如：

亚历克斯正在考虑以10亿美元的价格收购一家英国的初创公司。他非常有信心这会发生。苏桑也处于同样的情况。然而，她已经失去了希望。

输出为：

亚历克斯正在考虑以10亿美元的价格收购一家英国的初创公司。亚历克斯非常有信心这会发生。苏桑也处于同样的情况。然而，苏珊已经失去了希望。

再比如,

彼得是盖茨的朋友。但是盖茨不喜欢他

在这种情况下，输出为：

彼得是盖茨的朋友。但是盖茨不喜欢盖茨。

对!！这太吵了

使用spacy： 我已经使用NER提取了

Person

，但是如何适当地替换代词呢

代码：

---

我为您的两个示例编写了一个函数：

考虑使用更大的模型，例如

en_core\u web\u lg

，以获得更精确的标记

import spacy
from string import punctuation

nlp = spacy.load("en_core_web_lg")

def pronoun_coref(text):
    doc = nlp(text)
    pronouns = [(tok, tok.i) for tok in doc if (tok.tag_ == "PRP")]
    names = [(ent.text, ent[0].i) for ent in doc.ents if ent.label_ == 'PERSON']
    doc = [tok.text_with_ws for tok in doc]
    for p in pronouns:
        replace = max(filter(lambda x: x[1] < p[1], names),
                      key=lambda x: x[1], default=False)
        if replace:
            replace = replace[0]
            if doc[p[1] - 1] in punctuation:
                replace = ' ' + replace
            if doc[p[1] + 1] not in punctuation:
                replace = replace + ' '
            doc[p[1]] = replace
    doc = ''.join(doc)
    return doc

导入空间
从字符串导入标点符号
nlp=空间负荷（“核心网络负荷”）
def代词_coref（文本）：
doc=nlp（文本）
doc if中tok的代词=[（tok，tok.i）（tok.tag==“PRP”）]
name=[（ent.text，ent[0].i）对于doc.ents中的ent，如果ent.label==“PERSON”]
doc=[tok.text_，带文档中tok的w]
对于代词中的p：
替换=最大值（过滤器（λx:x[1]

有专门的库来解决相互引用问题。请参见下面的最小可复制示例：

import spacy
import neuralcoref

nlp = spacy.load('en_core_web_sm')
neuralcoref.add_to_pipe(nlp)
doc = nlp(
'''Alex is looking at buying a U.K. startup for $1 billion. 
He is very confident that this is going to happen. 
Sussan is also in the same situation. 
However, she has lost hope.
Peter is a friend of Gates. But Gates does not like him.
          ''')

print(doc._.coref_resolved)

Alex is looking at buying a U.K. startup for $1 billion. 
Alex is very confident that this is going to happen. 
Sussan is also in the same situation. 
However, Sussan has lost hope.
Peter is a friend of Gates. But Gates does not like Peter.
 

注意，如果您pip安装了neuralRef，您可能会遇到一些问题，因此最好从源代码构建它，正如我所概述的

import spacy
import neuralcoref

nlp = spacy.load('en_core_web_sm')
neuralcoref.add_to_pipe(nlp)
doc = nlp(
'''Alex is looking at buying a U.K. startup for $1 billion. 
He is very confident that this is going to happen. 
Sussan is also in the same situation. 
However, she has lost hope.
Peter is a friend of Gates. But Gates does not like him.
          ''')

print(doc._.coref_resolved)

Alex is looking at buying a U.K. startup for $1 billion. 
Alex is very confident that this is going to happen. 
Sussan is also in the same situation. 
However, Sussan has lost hope.
Peter is a friend of Gates. But Gates does not like Peter.