Overview of Natural Language Processing
Importance of data representation for computers to understand language
Overview of NLP challenges and how to tackle them with deep learning
Overview of word2vec algorithm for text classification
We will cover distributed data representations, such as word embeddings using the word2vec algorithm.
Once trained, the word embeddings can be used for variety of problems, including text classification.
Build a linguistic style model to extract features from a given set of texts using embeddings
Text classification will be used to determine the authors of an unknown set of documents. The trained text-classification model is then used to identify the right author for a given text document.
Create a neural machine translation model to convert text from one language to another
Learn the basic technique to translate human-readable text to machine-readable format, and how to use attention mechanisms to improve results - especially for long strings.
Closing Comments and Questions
Wrap-up, potential next steps, and Q&A
Quick overview of the next steps you could leverage to build and deploy your own applications
Tools, libraries, and frameworks: TensorFlow, Keras