Modern NLP using Deep Learning
Neural machine translation (NMT), Text summarization, Question Answering, Chatbot
What you will learn
Advance knowledge at modern NLP
Understand modern NLP techniques
Advance knowledge at modern DL
Understand modern DL techniques
You will learn the newest state-of-the-art Natural language processing (NLP) Deep-learning approaches.
Get state-of-the-art knowledge regarding
Validate your knowledge by answering short and very easy 3-question queezes of each lecture
Be able to complete the course by ~2 hours.
Neural machine translation (NMT)
A family of machine learning approaches used for natural language processing.
A technique that mimics cognitive attention.
An approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modelling entire sentences in a single integrated model.
An algorithm for training the weights of recurrent neural networks (RNNs).
An algorithm for evaluating the quality of text which has been machine-translated from one natural language to another.
A heuristic search algorithm that explores a graph by expanding the most promising node in a limited set.
A deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data.
An autoregressive language model that uses deep learning to produce human-like text.
A transformer-based machine learning technique for natural language processing (NLP) pre-training developed by Google.
An algorithmic technique that hashes similar input items into the same "buckets" with high probability.
A variant of ResNets where each layer's activations can be reconstructed exactly from the next layer's.
Introduces two techniques to improve the efficiency of Transformers.