时间戳

首页 > 解决方案 > 如何根据每个句子而不是通过文件匹配命名实体

python - 如何根据每个句子而不是通过文件匹配命名实体

问题描述

我有一个文本文件，我实现了 Polyglot NER 以从该文本文件中提取实体。然后我必须分割每个句子并匹配每个句子上提取的实体。匹配时，它应该给我输出。

from polyglot.text import Text
file = open('input_raw.txt', 'r')
input_file = file.read()
file = Text(input_file, hint_language_code='fa')

def return_match(entities_list, sentence):       ## Check if Chunks
    for term in entities_list:                  ## are in any of the entities
        ## Check each list in each Chunk object 
        ## and see if there's any matches.
        for entity in sentence.entities:
            if entity == term:
                return entity
    return None

def return_list_of_entities(file):
    list_entity = []
    for sentence in file.sentences:
        for entity in sentence.entities:
            list_entity.append(entity)
    return list_entity

list_entity = return_list_of_entities(file)
#sentence_number = 4 # Which sentence to check
for sentence in range(len(file.sentences)):
    sentencess = file.sentences[sentence]


match = return_match(list_entity, sentencess)

if match is not None:
    print("Entity Term " + str(match) +  
          " is in the sentence. '" + str(sentencess)+ "'")
else:
    print("Sentence '" + str(sentencess) + 
          "' doesn't contain any of the terms" + str(list_entity))

输入文件：

Bill Gates is the founder of Microsoft.
Trump is the president of the USA.
Bill Gates was a student in Harvard.

当我们实现 NER 时，实体看起来像：

list_etity：

Bill Gates, Microsoft, Trump, USA, Bill Gate, Harvard

当我们将实体与第一句话匹配时，它给出：

电流输出：

(Bill Gates, Bill Gates, Microsoft)

预期输出：

(Bill Gates, Microsoft) # this is from the first sentence and should contine
(Trump, USA) 
(Bill Gates, Harvard)

标签： pythonpython-3.x

解决方案

from polyglot.text import Text
import json
file = open('input_raw.txt', 'r')
input_file = file.read()
file = Text(input_file, hint_language_code='fa')

result = set()
entities_with_tag = []
def return_match(entities_list, sentence):  # Check if Chunks
    for i in range(len(sentence.entities)):
        for j in range(len(entities_list)):
            if entities_list[j] == sentence.entities[i]:
                # result.append(sentence.entities[i])
                result.add(str(sentence.entities[i]))
                entities_with_tag.append(sentence.entities[i])

def return_list_of_entities(file):
    list_entity = []
    for sentence in file.sentences:
        for entity in sentence.entities:
            list_entity.append(entity)
    return list_entity

list_entity = return_list_of_entities(file)

def return_sentence_number():
    for i in range(len(file.sentences)):
        sentence_no = file.sentences[i]
        return sentence_no

sent_no = return_sentence_number()
return_match(list_entity, sent_no)
print("Entity Term " + str(result) + " is in the sentence. '" + str(sent_no) + "'")

推荐阅读