Deep learning for NLP crash course at ABBYY.
Suggested textbook: Neural Network Methods in Natural Language Processing by Yoav Goldberg
Sentiment analysis on the IMDB movie review dataset: a short overview of classical machine learning for NLP + indecently brief intro to keras.
Run in Google Colab | View source on GitHub |
Meet the Word Embeddings: an unsupervised method to capture some fun relationships between words.
Phrases similarity with word embeddings model + word based machine translation without parallel data (with MUSE word embeddings).
Run in Google Colab | View source on GitHub |
Introduction to PyTorch. Implementation of pet linear regression on pure numpy and pytorch. Implementations of CBoW, skip-gram, negative sampling and structured Word2vec models.
Run in Google Colab | View source on GitHub |
Introduction to convolutional networks. Relations between convolutions and n-grams. Simple surname detector on character-level convolutions + fun visualizations.
Run in Google Colab | View source on GitHub |
RNNs for text classification. Simple RNN implementation + memorization test. Surname detector in multilingual setup: character-level LSTM classifier.
Run in Google Colab | View source on GitHub |
RNNs for sequence labelling. Part-of-speech tagger implementations based on word embeddings and character-level word embeddings.
Run in Google Colab | View source on GitHub |
Character-level language model for Russian troll tweets generation: fixed-window model via convolutions and RNN model.
Simple conditional language model: surname generation given source language.
And Toxic Comment Classification Challenge - to apply your skills to a real-world problem.
Run in Google Colab | View source on GitHub |
Word-level language model for poetry generation. Pet examples of transfer learning and multi-task learning applied to language models.
Run in Google Colab | View source on GitHub |