Neural machine translation (NMT), Text summarization, Question Answering, Chatbot
You will learn the newest state-of-the-art Natural language processing (NLP) Deep-learning approaches.
You will
-
Get state-of-the-art knowledge regarding
-
NMT
-
Text summarization
-
QA
-
Chatbot
-
-
Validate your knowledge by answering short and very easy 3-question queezes of each lecture
-
Be able to complete the course by ~2 hours.
Syllabus
-
Neural machine translation (NMT)
-
Seq2seq
A family of machine learning approaches used for natural language processing. -
Attention
A technique that mimics cognitive attention. -
NMT
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. -
Teacher-forcing
An algorithm for training the weights of recurrent neural networks (RNNs). -
BLEU
An algorithm for evaluating the quality of text which has been machine-translated from one natural language to another. -
Beam search
A heuristic search algorithm that explores a graph by expanding the most promising node in a limited set.
-
-
Text summarization
-
Transformer
A deep learning model that adopts the mechanism of self-attention, differentially weighting the significance of each part of the input data.
-
-
Question Answering
-
GPT-3
An autoregressive language model that uses deep learning to produce human-like text. -
BERT
A transformer-based machine learning technique for natural language processing (NLP) pre-training developed by Google.
-
-
Chatbot
-
LSH
An algorithmic technique that hashes similar input items into the same “buckets” with high probability. -
RevNet
A variant of ResNets where each layer’s activations can be reconstructed exactly from the next layer’s. -
Reformer
Introduces two techniques to improve the efficiency of Transformers.
-
Resources
-
Wikipedia
-
Coursera