#898 · Primary category: Education & Research

DeepNLP-Course

colab-notebook deep-learning keras nlp pytorch

Deep NLP Course

Project last updated:07/20/19

GitHub Stars

631

Forks

162

Contributors

1

License

Other

Why we included this project

Deep NLP Course began as a crash course taught inside ABBYY, and the notebooks still hold up as a hands-on way to learn NLP. Fourteen weeks of material pair a short concept write-up with a Colab notebook, so you can work through everything in the browser without installing anything locally. The path is sensible: sentiment classification and word embeddings come first, then CNNs and RNNs, then sequence labeling, and it closes on seq2seq with attention, transformers, and dialogue systems. Along the way you build CBoW and skip-gram, a character-level LSTM surname detector, a part-of-speech tagger, and a Transformer for summarization, which makes the mechanics stick far better than reading about them. Because every notebook ships in Russian and English, it is also a solid backbone for a team running an internal NLP training track.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category