The main purpose of this work is to understand about the word embedding (part of language modelling techniques for NLP), its applications, and how to build a model that can be used for text processing with the help of some related Deep Learning packages/libraries for NLP.
- What is word embedding for text, RNN
- Algorithms used for learning word embedding from text data (eg. fasttext, glove, word2vec developed by Mikolov et al that is used for learning vector representations of words)
- Some insights about Deep learning packages (eg. TensorFlow)
Apply word embedding in deep learning (Python) (dataset can be chosen from Kaggle)
To run the project, please download the data zip file and extract it into folder name data, put it into the same place with other Jupyter Notebooks.
Link: https://drive.google.com/drive/folders/13UluRzWGIraS9ugfuS2qdz3JKxS5etTn?usp=sharing