All Projects → zqhZY → Semanaly

zqhZY / Semanaly

semantic analysis using word2vector, doc2vector,lstm and other method. mainly for text similarity analysis.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Semanaly

Abstractive Summarization
Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.
Stars: ✭ 128 (-10.49%)
Mutual labels:  lstm
Deeplearningfornlpinpytorch
An IPython Notebook tutorial on deep learning for natural language processing, including structure prediction.
Stars: ✭ 1,744 (+1119.58%)
Mutual labels:  lstm
Actionrecognition
Explore Action Recognition
Stars: ✭ 139 (-2.8%)
Mutual labels:  lstm
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-6.29%)
Mutual labels:  lstm
Easyocr
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stars: ✭ 13,379 (+9255.94%)
Mutual labels:  lstm
Vpilot
Scripts and tools to easily communicate with DeepGTAV. In the future a self-driving agent will be implemented.
Stars: ✭ 136 (-4.9%)
Mutual labels:  lstm
Chinese Chatbot
中文聊天机器人,基于10万组对白训练而成,采用注意力机制,对一般问题都会生成一个有意义的答复。已上传模型,可直接运行,跑不起来直播吃键盘。
Stars: ✭ 124 (-13.29%)
Mutual labels:  lstm
Image Caption Generator
[DEPRECATED] A Neural Network based generative model for captioning images using Tensorflow
Stars: ✭ 141 (-1.4%)
Mutual labels:  lstm
Lstm Crypto Price Prediction
Predicting price trends in cryptomarkets using an lstm-RNN for the use of a trading bot
Stars: ✭ 136 (-4.9%)
Mutual labels:  lstm
Ethnicolr
Predict Race and Ethnicity Based on the Sequence of Characters in a Name
Stars: ✭ 137 (-4.2%)
Mutual labels:  lstm
Stockprediction
Plain Stock Close-Price Prediction via Graves LSTM RNNs
Stars: ✭ 134 (-6.29%)
Mutual labels:  lstm
Handwriting Synthesis
Implementation of "Generating Sequences With Recurrent Neural Networks" https://arxiv.org/abs/1308.0850
Stars: ✭ 135 (-5.59%)
Mutual labels:  lstm
Question Pairs Matching
第三届魔镜杯 智能客服问题相似性算法设计 第12名解决方案
Stars: ✭ 138 (-3.5%)
Mutual labels:  lstm
E3d lstm
e3d-lstm; Eidetic 3D LSTM A Model for Video Prediction and Beyond
Stars: ✭ 129 (-9.79%)
Mutual labels:  lstm
Richwordsegmentor
Neural word segmentation with rich pretraining, code for ACL 2017 paper
Stars: ✭ 140 (-2.1%)
Mutual labels:  lstm
Image Caption Generator
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Stars: ✭ 126 (-11.89%)
Mutual labels:  lstm
Ncrfpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+1135.66%)
Mutual labels:  lstm
Rnn poetry generator
基于RNN生成古诗
Stars: ✭ 143 (+0%)
Mutual labels:  lstm
Deep Learning Resources
A Collection of resources I have found useful on my journey finding my way through the world of Deep Learning.
Stars: ✭ 141 (-1.4%)
Mutual labels:  lstm
Document Classifier Lstm
A bidirectional LSTM with attention for multiclass/multilabel text classification.
Stars: ✭ 136 (-4.9%)
Mutual labels:  lstm

semanaly

semantic analysis using word2vector, doc2vector and other method. mainly for text similarity analysis. related link here

useage

word2vector

data prepare

unzip dataset/me_train.zip
python read_data.py (in word2vector dir)

train for w2v and d2v

mkdir model
python word2vector.py (in word2vector dir)
python doc2vector.py (in word2vector dir)

test for text similarity use word2vector

python sample.py
python shottext.py

lstm

cd lstm
python lstm.py
python shottext_lstm.py

textclassfier

  • demo text classfier using word2vector、cnn、lstm implemented by pytorch.
  • kfold implemented for train

tools

tools for data preprocess

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].