RiverText is a framework that standardizes the Incremental Word Embeddings proposed in the state-of-art. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!

🎓 Diploma Thesis | A Word2vec comparative study of CBOW and Skipgram

COVID-19 Arabic Word embeddings is a domain- specific pre-trained distributed word representation of COVID-19 Tweets which aims to provide the Arabic NLP research community with free to use and powerful word embedding models.

This repository contains implementations of text classification using a Rule-Based Classifier and Bag of Words model, as well as word embeddings using the Skip-gram model of Word2Vec. It includes detailed preprocessing steps, model training, and relevant references.

Continuous skip-gram model for generating word embeddings for customer complaints data.

Pytorch implementation for Incremental SkipGram with Negative Sampling