deep-nlp-links

• a good introduction and overview on CNNs in three steps:

https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner's-Guide-To-Understanding-Convolutional-Neural-Networks/

https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner's-Guide-To-Understanding-Convolutional-Neural-Networks-Part-2/

https://adeshpande3.github.io/adeshpande3.github.io/The-9-Deep-Learning-Papers-You-Need-To-Know-About.html

• a good introduction to bert and how to use it:

https://arxiv.org/pdf/1810.04805.pdf

https://huggingface.co/transformers/model_doc/bert.html

https://jalammar.github.io/illustrated-bert/

• an example to how to fine-tune it:

  https://medium.com/swlh/painless-fine-tuning-of-bert-in-pytorch-b91c14912caa

• Stanford Deep NLP 2019:

http://onlinehub.stanford.edu/youtube-cs224n-natural-language-processing-with-deep-learning-winter-2019

session1,2: good to get an appropriate start point and general view of deep natural language processing fundamentals.

session3: an introduction to neural networks

session4: get a little deep into basics of backpropagation

session5: dependency parsing (I do not suggest this unless parsing is the task you are working on.)

session6,7,8: are about RNNs. It disscusses different types of it, and following a main stream it sheds light on the methods solved its challenges. It is proposed in a well-defined structure with appropriate amount of mathematical fundamentals. These are all too delicious to follow :)

• Andrew Ng ML:

week 10: a set of introductions to large scale machine learning that includes a method to apply ml algorithms in a map-reduce based framework.

week 11: an introduction to ocr and image processing. It really helped me to get much more interested in ML than before. Actually, from then I'm much more ml fan than just text-mining, my first love in computer science.

• Deep Sentiment Analysis: https://towardsdatascience.com/fine-grained-sentiment-analysis-in-python-part-1-2697bb111ed4