Stars
CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition
A C-LSTM neural network for text classification with attention, a neural architecture for solving classification task using union of convolutional(CNN) and recurrent neural network(RNN).
Using CNN & RNN & GRU & LSTM & BiRNN & BiGRU & BiLSTM & Transformers for Emotions Sentimental Analysis
This project aims to classify text data into multiple categories using various deep learning architectures like Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Bidirectional R…
This GitHub repository provides an implementation of the paper "MAGNET: Multi-Label Text Classification using Attention-based Graph Neural Network" . MAGNET is a state-of-the-art approach for multi…
sentiment analysis is done using two machine learning that are SVM and random forest and two deep learning algorithms that are LSTM and CNN. the US Airline dataset is use to train the model to do s…
model：Navie Bayes/Random Forest/SVM/Fasttext/TextCNN. Using one-hot/tf-idf/focal-loss/SMOTE
新闻短文本分类，可以在此基础上进一步完善实现其他短文本分类任务，欢迎fork 和 star。
实现TextCNN，TextRNN，BiLSTM，Transformer，Bert等模型
Click below to checkout the website
This is a basic code repository for text sentiment analysis. It is used to store and open source the mid-term report code, and is also for beginners to easily review. The warehouse contains the cod…
IMDb review sentiment analysis model created in TensorFlow with CNN+LSTM+GloVe Twiter Embeddings.
## 数据挖掘流程 **（一）数据读取** - 读取数据，并进行展示 - 统计数据各项指标 - 明确数据规模与要完成的任务 **（二）特征理解分析** - 单特征分析，逐个变量分析其对结果的影响 - 多变量统计分析，综合考虑多种情况影响 - 统计绘图得出结论 **（三）数据清洗与预处理** - 对缺失值进行填充 - 特征标准化/归一化 - 筛选有价值的特征 - 分析特征之间的相关性 **（四…
Aspect Categorization Model using CNNs: Classifies product aspects from user reviews using GloVe embeddings and Keras. Includes hyperparameter tuning and visualization.
NLP with pre-defined words Embeddings with GloVe and CNN for sentimental analysis on Twitter
使用各种模型结构，例如textCNN、textRNN、Transformer、CNN+RNN、Bi-LSTM的文本匹配源码项目
Text Classification using Convolution Neural Networks.
Text classification experiments using TextCNNs and Bi-attentive Classification Networks