地址分词

中文地址分词,ner

Posted by koryako on January 24, 2022

地址分词

https://github.com/geeklili/albert-finetune

google 的bert 预训练模型[bert 源码解读] https://www.jianshu.com/p/3d0bb34c488a ,她的中文变体 albert 和roberta都是在其源码的基础上改造而成,并使用中文语料重新训练而成

我们使用 基于BERT预训练的中文命名实体识别TensorFlow实现源码 进行实际的部署, 他的tf2.0 代码 可以参考 2.0 代码

  1. https://github.com/google-research/bert#fine-tuning-with-bert (谷歌开源BERT)

  2. https://blog.csdn.net/macanv/article/details/85684284 (基于BERT预训练的中文命名实体识别TensorFlow实现)

  3. https://www.jianshu.com/p/b05e50f682dd(序列标注——实体识别BERT-BLSTM-CRF)

  4. https://www.jianshu.com/p/3d0bb34c488a(BERT的demo运行)

  5. https://python.ctolib.com/ProHiryu-albert-chinese-ner.html(使用预训练语言模型ALBERT做中文NER)

  6. https://github.com/kyzhouhzau/BERT-NER(输出带acc)

  7. https://github.com/brightmart/albert_zh(ALBert 预训练模型)

  8. https://github.com/macanv/BERT-BiLSTM-CRF-NER(BERT-BiLSTM-CRF-NER常用版)

  9. https://www.jianshu.com/p/1d6689851622(五分钟搭建一个基于BERT的NER模型)

  10. https://github.com/BrikerMan/Kashgari(快速搭建NER框架)

  11. https://github.com/grallage/ALBERT-BiLSTM-CRF-NER(ALBERT-BiLSTM-CRF-NER)

bert 预训练语言理解问题 原始bert 技术分析 bert 发展史

https://github.com/namisan/mt-dnn

https://github.com/rasbt/deeplearning-models

Bert时代的创新:Bert在NLP各领域的应用进展

多标签分类

Ideas from google’s bert for language understanding: Pre-train TextCNN

使用Bert预训练模型文本分类(内附源码)

#https://github.com/google-research/football #https://github.com/mnicnc404/CartoonGan-tensorflow #https://saic-violet.github.io/texturedavatar/ #http://densepose.org/ #https://arxiv.org/abs/1905.08776 #!pip install bert-tensorflow #https://blog.csdn.net/broccoli2/article/details/108952022?utm_source=app 保存为pb

#!pip install bert-serving-server # server

#!pip install bert-serving-client # client, independent of ‘bert-serving-server’ import bert from bert import run_classifier from bert import optimization from bert import tokenization #载入依赖 import pandas as pd import os import csv import time import datetime import random import json import warnings from collections import Counter from math import sqrt import gensim import numpy as np import tensorflow as tf from sklearn.metrics import roc_auc_score, accuracy_score, precision_score, recall_score from sklearn import model_selection, preprocessing, linear_model, naive_bayes, metrics, svm from keras.models import Sequential from keras import layers