amansrivastava17 / Lstm Siamese Text Similarity
Licence: mit
⚛️ It is keras based implementation of siamese architecture using lstm encoders to compute text similarity
Stars: ✭ 216
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Lstm Siamese Text Similarity
Tensorflow Sentiment Analysis On Amazon Reviews Data
Implementing different RNN models (LSTM,GRU) & Convolution models (Conv1D, Conv2D) on a subset of Amazon Reviews data with TensorFlow on Python 3. A sentiment analysis project.
Stars: ✭ 34 (-84.26%)
Mutual labels: lstm, lstm-neural-networks
Contextual Utterance Level Multimodal Sentiment Analysis
Context-Dependent Sentiment Analysis in User-Generated Videos
Stars: ✭ 86 (-60.19%)
Mutual labels: lstm, lstm-neural-networks
Image Captioning
Image Captioning: Implementing the Neural Image Caption Generator with python
Stars: ✭ 52 (-75.93%)
Mutual labels: lstm, lstm-neural-networks
Chameleon recsys
Source code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (-6.48%)
Mutual labels: lstm, lstm-neural-networks
Deep Generation
I used in this project a reccurent neural network to generate c code based on a dataset of c files from the linux repository.
Stars: ✭ 101 (-53.24%)
Mutual labels: lstm, lstm-neural-networks
Deep Learning Time Series
List of papers, code and experiments using deep learning for time series forecasting
Stars: ✭ 796 (+268.52%)
Mutual labels: lstm, lstm-neural-networks
Lstm anomaly thesis
Anomaly detection for temporal data using LSTMs
Stars: ✭ 178 (-17.59%)
Mutual labels: lstm, lstm-neural-networks
Paraphraser
Sentence paraphrase generation at the sentence level
Stars: ✭ 283 (+31.02%)
Mutual labels: lstm, lstm-neural-networks
Text predictor
Char-level RNN LSTM text generator📄.
Stars: ✭ 99 (-54.17%)
Mutual labels: lstm, lstm-neural-networks
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-55.09%)
Mutual labels: lstm, lstm-neural-networks
Stockpriceprediction
Stock Price Prediction using Machine Learning Techniques
Stars: ✭ 700 (+224.07%)
Mutual labels: lstm, lstm-neural-networks
Image Caption Generator
[DEPRECATED] A Neural Network based generative model for captioning images using Tensorflow
Stars: ✭ 141 (-34.72%)
Mutual labels: lstm, lstm-neural-networks
Predictive Maintenance Using Lstm
Example of Multiple Multivariate Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras.
Stars: ✭ 352 (+62.96%)
Mutual labels: lstm, lstm-neural-networks
Simple Chatbot Keras
Design and build a chatbot using data from the Cornell Movie Dialogues corpus, using Keras
Stars: ✭ 30 (-86.11%)
Mutual labels: lstm, lstm-neural-networks
Personality Detection
Implementation of a hierarchical CNN based model to detect Big Five personality traits
Stars: ✭ 338 (+56.48%)
Mutual labels: lstm, lstm-neural-networks
Bitcoin Price Prediction Using Lstm
Bitcoin price Prediction ( Time Series ) using LSTM Recurrent neural network
Stars: ✭ 67 (-68.98%)
Mutual labels: lstm, lstm-neural-networks
OCR
Optical character recognition Using Deep Learning
Stars: ✭ 25 (-88.43%)
Mutual labels: lstm, lstm-neural-networks
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (-58.8%)
Mutual labels: lstm, lstm-neural-networks
Cnn lstm for text classify
CNN, LSTM, NBOW, fasttext 中文文本分类
Stars: ✭ 90 (-58.33%)
Mutual labels: lstm, lstm-neural-networks
Repo 2016
R, Python and Mathematica Codes in Machine Learning, Deep Learning, Artificial Intelligence, NLP and Geolocation
Stars: ✭ 103 (-52.31%)
Mutual labels: lstm, lstm-neural-networks
Text Similarity Using Siamese Deep Neural Network
Siamese neural network is a class of neural network architectures that contain two or more identical subnetworks. identical here means they have the same configuration with the same parameters and weights. Parameter updating is mirrored across both subnetworks.
It is a keras based implementation of deep siamese Bidirectional LSTM network to capture phrase/sentence similarity using word embeddings.
Below is the architecture description for the same.
Install dependencies
pip install -r requirements.txt
Usage
Training
from model import SiameseBiLSTM
from inputHandler import word_embed_meta_data, create_test_data
from config import siamese_config
import pandas as pd
############ Data Preperation ##########
df = pd.read_csv('sample_data.csv')
sentences1 = list(df['sentences1'])
sentences2 = list(df['sentences2'])
is_similar = list(df['is_similar'])
del df
######## Word Embedding ############
tokenizer, embedding_matrix = word_embed_meta_data(sentences1 + sentences2, siamese_config['EMBEDDING_DIM'])
embedding_meta_data = {
'tokenizer': tokenizer,
'embedding_matrix': embedding_matrix
}
## creating sentence pairs
sentences_pair = [(x1, x2) for x1, x2 in zip(sentences1, sentences2)]
del sentences1
del sentences2
######## Training ########
class Configuration(object):
"""Dump stuff here"""
CONFIG = Configuration()
CONFIG.embedding_dim = siamese_config['EMBEDDING_DIM']
CONFIG.max_sequence_length = siamese_config['MAX_SEQUENCE_LENGTH']
CONFIG.number_lstm_units = siamese_config['NUMBER_LSTM']
CONFIG.rate_drop_lstm = siamese_config['RATE_DROP_LSTM']
CONFIG.number_dense_units = siamese_config['NUMBER_DENSE_UNITS']
CONFIG.activation_function = siamese_config['ACTIVATION_FUNCTION']
CONFIG.rate_drop_dense = siamese_config['RATE_DROP_DENSE']
CONFIG.validation_split_ratio = siamese_config['VALIDATION_SPLIT']
siamese = SiameseBiLSTM(CONFIG.embedding_dim , CONFIG.max_sequence_length, CONFIG.number_lstm_units , CONFIG.number_dense_units, CONFIG.rate_drop_lstm, CONFIG.rate_drop_dense, CONFIG.activation_function, CONFIG.validation_split_ratio)
best_model_path = siamese.train_model(sentences_pair, is_similar, embedding_meta_data, model_save_directory='./')
Testing
from operator import itemgetter
from keras.models import load_model
model = load_model(best_model_path)
test_sentence_pairs = [('What can make Physics easy to learn?','How can you make physics easy to learn?'),('How many times a day do a clocks hands overlap?','What does it mean that every time I look at the clock the numbers are the same?')]
test_data_x1, test_data_x2, leaks_test = create_test_data(tokenizer,test_sentence_pairs, siamese_config['MAX_SEQUENCE_LENGTH'])
preds = list(model.predict([test_data_x1, test_data_x2, leaks_test], verbose=1).ravel())
results = [(x, y, z) for (x, y), z in zip(test_sentence_pairs, preds)]
results.sort(key=itemgetter(2), reverse=True)
print results
References:
- Siamese Recurrent Architectures for Learning Sentence Similarity (2016)
- Inspired from Tensorflow Implementation of https://github.com/dhwajraj/deep-siamese-text-similarity
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].