def __init__(self,
entity2relations_dict='data/entity2relations_dict.pkl',
seqPair2similarity_dict='data/seqPair2similarity_dict.pkl'):
self._entity2relations = self._load_dict(entity2relations_dict)
self._seqPair2similarity = self._load_dict(seqPair2similarity_dict)
self._similarity_dict_path = seqPair2similarity_dict
self._relation_paths_dict_path = entity2relations_dict
self._model = BertSim()
self._model.mode = tf.estimator.ModeKeys.PREDICT
def __init__(self):
#加载微调过的文本匹配模型
self.simmer = BertSim()
self.tokenizer = BertTokenizer.from_pretrained(BERT_ID)
self.device = torch.device('cuda:0')
self.simmer.load_state_dict(torch.load('../data/model/similarity.pt'))
self.simmer.to(self.device)
print('bert相似度匹配模型加载完成')
print('tuple extractor loaded')
def __init__(self):
try:
self.entity2relations_dic = pickle.load(
open('../data/entity2relation_dic.pkl', 'rb'))
except:
self.entity2relations_dic = {}
try:
self.sentencepair2sim = pickle.load(
open('../data/sentencepair2sim_dic.pkl', 'rb'))
except:
self.sentencepair2sim = {}
self.simmer = BertSim()
self.simmer.set_mode(tf.estimator.ModeKeys.PREDICT)
print('tuples extractor loaded')
def __init__(self):
#加载一些缓存
try:
self.entity2relations_dic = pickle.load(open('../data/entity2relation_dic.pkl','rb'))
except:
self.entity2relations_dic = {}
#加载基于tensorflow的微调过的文本匹配模型
self.simmer = BertSim()
self.simmer.set_mode(tf.estimator.ModeKeys.PREDICT)
print ('bert相似度匹配模型加载完成')
#加载简单-复杂问题分类模型
#self.question_classify_model = get_model()
print ('问题分类模型加载完成')
print ('tuples extractor loaded')
import numpy as np
import pandas as pd
import urllib.request
import urllib.parse
import tensorflow as tf
from db import load_data_kudu
from global_config import Logger
sys.path.append('/home/mqq/zwshi/bert/')
from similarity import BertSim
# 模块导入 https://blog.csdn.net/xiongchengluo1129/article/details/80453599
loginfo = Logger("recommend_articles.log", "info")
file = "./NERdata/q_t_a_testing_predict.txt"
bs = BertSim()
bs.set_mode(tf.estimator.ModeKeys.PREDICT)
def dataset_test():
'''
用训练问答对中的实体+属性，去知识库中进行问答测试准确率上限
:return:
'''
with open(file) as f:
total = 0
recall = 0
correct = 0
for line in f:
question, entity, attribute, answer, ner = line.split("\t")