gensim-word2vec topic
wembedder
Wikidata embedding
word-embeddings-from-scratch
Creating word embeddings from scratch and visualize them on TensorBoard. Using trained embeddings in Keras.
Reuters-21578-Classification
Text classification with Reuters-21578 datasets using Gensim Word2Vec and Keras LSTM
twitter_sentiment_analysis_word2vec_convnet
Twitter Sentiment Analysis with Gensim Word2Vec and Keras Convolutional Network
Classification_Benchmarks_Benglai_NLP
Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network
Case2Vec
A simple web application for searching Word2Vec embeddings derived from approximately 2,000 law reports published by the The Incorporated Council of Law Reporting for England & Wales (https://www.iclr...
Twitter-LDA
Code to run LDA algorithm on Twitter/Foursquare scraped data.
TwitterSentimentAnalysis
Sentiment analysis for Twitter's tweet (in Indonesia language) was built with 3 models to get a comparison in determining which model gives the best results for predicting a tweet to have a positive o...
ArWordVec
ArWordVec is a collection of pre-trained word embedding model built from huge repository of Arabic tweets in different topics. The aim of these models is to support the community in their Arabic NLP-b...
ensemble-roberta-fasttext-vietnamese
Ensemble PhoBERT with FastText Embedding to improve performance on Vietnamese Sentiment Analysis tasks.