- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition: https://learning.oreilly.com/library/view/hands-on-machine-learning/9781492032632/
- Dive into Deep Learning: http://d2l.ai/
- https://keras.io/getting_started/intro_to_keras_for_engineers/
- https://keras.io/examples/nlp/masked_language_modeling/
- https://keras.io/examples/nlp/text_classification_from_scratch/
- https://keras.io/examples/nlp/pretrained_word_embeddings/
- https://keras.io/examples/nlp/text_classification_with_transformer/
- Double-Hard Debias:Tailoring Word Embeddings for Gender Bias Mitigation
- Proceedings of the First Workshop on Gender Bias in Natural Language Processing
- Have an in-depth Understanding of the following concepts
- Logistic Regression, Linear Regression, and Neural Network.
- Loss functions for classification
- Activation functions
- Read PCA and CNN and how they work.
- Implement a Logistic Regression and Neural Network in Keras.
-
Book chapters
- Chapter 13. Loading and Preprocessing Data with TensorFlow
- Chapter 15. Processing Sequences Using RNNs and CNNs
- Chapter 16. Natural Language Processing with RNNs and Attention
-
Articles and papers on BIAS
- http://web.cs.ucla.edu/~kwchang/talks/emnlp19-fairnlp/
- Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word - Embeddings. NIPS 2016.
- Ninareh Mehrabi, Thamme Gowda, Fred Morstatter, Nanyun Peng, Aram Galstyan. 2019. Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition.
- Vaibhav Kumar, Tenzin Singhay Bhotia, Vaibhav Kumar, Tanmoy Chakraborty. 2020 Nurse is Closer to Woman than Surgeon? Mitigating Gender-Biased Proximities in Word Embeddings. TACL.
-
Code in Github
- Logistic Regression and Neural Network in Keras.