Chapter 3

• Word representations: https://dl.acm.org/citation.cfm?id=1858721
• One-hot encoding: https://machinelearningmastery.com/how-to-one-hot-encode-sequence-data-in-python/
• Representational learning: https://github.com/anujgupta82/Representation-Learning-for-NLP
• N-grams: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.53.9367
• TF-IDF: https://nlp.stanford.edu/IR-book/html/htmledition/inverse-document-frequency-1.html
• Mikolov et al. 2013: https://arxiv.org/abs/1310.4546
• Maas and cgpotts paper: https://web.stanford.edu/~cgpotts/papers/wvSent_acl2011.pdf
• Bag of words in scikit-learn: http://scikit-learn.org/stable/modules/feature_extraction.html#the-bag-of-words-representation
• Kaggle word2vec https://www.kaggle.com/c/word2vec-nlp-tutorial
• Heap's law: https://en.wikipedia.org/wiki/Heaps%27_law
• Distributed representations of sentences and documents, Mikolov et al: https://cs.stanford.edu/~quocle/paragraph_vector.pdf
• CBOW: https://towardsdatascience.com/understanding-feature-engineering-part-4-deep-learning-methods-for-text-data-96c44370bbfa
• Skip-gram: McCormick, C. (2016, April 19), Word2Vec Tutorial - The Skip-Gram Model http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/
• TensorFlow implementation of word2vec: https://github.com/tensorflow/tensorflow/blob/r1.1/tensorflow/examples/tutorials/word2vec/word2vec_basic.py
• Word2vec explained: https://arxiv.org/abs/1411.2738
• Deriving negative sampling: https://arxiv.org/abs/1402.3722
• Compositional distributional semantics: https://youtu.be/hTmKoHJw3Mg
• The fastText and skipgram: http://debajyotidatta.github.io/nlp/deep/learning/word-embeddings/2016/09/28/fast-text-and-skip-gram/
• The skip-gram and CBOW: https://iksinc.online/tag/continuous-bag-of-words-cbow/
• Stanford lectures on CBOW and skip-gram: https://cs224d.stanford.edu/lecture_notes/notes1.pdf
• http://mccormickml.com/assets/word2vec/Alex_Minnaar_Word2Vec_Tutorial_Part_II_The_Continuous_Bag-of-Words_Model.pdf
• The fasttext PyTorch: https://github.com/PetrochukM/PyTorch-NLP
• Levy, Omer and Goldberg Yoav (2014), Dependency-Based Word Embeddings, 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014-Proceedings of the Conference, 2. 302-308. 10.3115/v1/P14-2050
• Notes on Noise Contrastive Estimation and Negative Sampling: https://arxiv.org/abs/1410.8251
• Sebastian Ruder, on word embeddings - Part 2: Approximating the Softmax, http://ruder.io/word-embeddings-softmax, 2016.
• Scalable hierarchical distributed language model. http://papers.nips.cc/paper/3583-a-scalable-hierarchical-distributed-language-model.pdf
• Softmax function and its derivative. https://eli.thegreenplace.net/2016/the-softmax-function-and-its-derivative/
• What is Softmax Regression and How is it Related to Logistic Regression?, Sebastian Raschka. https://www.kdnuggets.com/2016/07/softmax-regression-related-logistic-regression.html
• https://web.stanford.edu/class/cs224n/reports/2758157.pdf
• Softmax regression, http://ufldl.stanford.edu/tutorial/supervised/SoftmaxRegression/
• Google Allo: https://research.googleblog.com/2016/05/chat-smarter-with-allo.html
• Hierarchical Probabilistic Neural Network Language Model, Morin and Bengio, 2005, https://www.iro.umontreal.ca/~lisa/pointeurs/hierarchical-nnlm-aistats05.pdf
• A Scalable Hierarchical Distributed Language Model. Mnih, Andriy and Hinton, Geoffrey E. 2009, https://papers.nips.cc/paper/3583-a-scalable-hierarchical-distributed-language-model
• Self Organised Hierarchical Softmax, arXiv:1707.08588v1 [cs.CL] 26 Jul 2017
• Effective Text Clustering Method Based on Huffman Encoding Algorithm, Nikhil Pawar, 2012, https://www.ijsr.net/archive/v3i12/U1VCMTQ1NjE=.pdf
• Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean, Distributed representations of words and phrases and their compositionality, In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013, Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, pages 3111–3119, 2013.
• http://debajyotidatta.github.io/nlp/deep/learning/word-embeddings/2016/09/28/fast-text-and-skip-gram/
• https://github.com/nzw0301/keras-examples/blob/master/Skip-gram-with-NS.ipynb