python - 使用 python 和 nltk 从文本文件中提取候选人的姓名

Question

import re
import spacy
import nltk
from nltk.corpus import stopwords
stop = stopwords.words('english')
from nltk.corpus import wordnet

inputfile = open('inputfile.txt', 'r')
String= inputfile.read()
nlp = spacy.load('en_core_web_sm')

def candidate_name_extractor(input_string, nlp):
    input_string = str(input_string)

    doc = nlp(input_string)

    # Extract entities
    doc_entities = doc.ents

    # Subset to person type entities
    doc_persons = filter(lambda x: x.label_ == 'PERSON', doc_entities)
    doc_persons = filter(lambda x: len(x.text.strip().split()) >= 2, doc_persons)
    doc_persons = list(map(lambda x: x.text.strip(), doc_persons))
    print(doc_persons)
    # Assuming that the first Person entity with more than two tokens is the candidate's name
    candidate_name = doc_persons[0]
    return candidate_name

if __name__ == '__main__':
    names = candidate_name_extractor(String, nlp)

print(names)

我想从文本文件中提取候选人的姓名，但它返回错误的值。当我删除带有 map 的列表时， map 也无法工作并给出错误

Answer 1

import re
import nltk
from nltk.corpus import stopwords
stop = stopwords.words('english')
from nltk.corpus import wordnet

String = 'Ravana was killed in a war'

Sentences = nltk.sent_tokenize(String)
Tokens = []
for Sent in Sentences:
    Tokens.append(nltk.word_tokenize(Sent)) 
Words_List = [nltk.pos_tag(Token) for Token in Tokens]

Nouns_List = []

for List in Words_List:
    for Word in List:
        if re.match('[NN.*]', Word[1]):
             Nouns_List.append(Word[0])

Names = []
for Nouns in Nouns_List:
    if not wordnet.synsets(Nouns):
        Names.append(Nouns)

print (Names)

检查此代码。我得到 Ravana 作为输出。

编辑:

我使用简历中的几句话创建了一个文本文件，并将其作为程序的输入。下面仅显示更改的代码部分:

import io

File = io.open("Documents\\Temp.txt", 'r', encoding = 'utf-8')
String = File.read()
String = re.sub('[/|.|@|%|\d+]', '', String)

它会返回 wordnet 语料库中没有的所有名称，例如我的名字、我的房屋名称、地点、大学名称和地点。