The following 10 courses can be taken in any sequence, it also contains lot many free tutorials from Stanford and other universities. Overall this list is meant to give you that edge in NLP knowledge to shape your career better. We have tried to cover every possible and available topics in NLP out there. One course doesn't teach everything you might need, hence you will have to combine one or two courses to get the full benefits.
This course will cover Word Vectors, Word Senses, Neural Networks, Backpropagation, Dependency parsing, Language Models, Vanishing Gradients, Recurrent Neural Networks, Transition Seq2Seq, Practical Tips for Projects, Question & Answering, Convolution Network for NLP, Subword Models, Contextual word embeddings, Transformer and self-attestation, NLG(Natual Language Generation), Coreference resolution, TreeRNNs, Bias in AI, Future of NLP.
This course was taken by 47,000 members. It covers, Text classification, Neural Networks, Hashing trick, Sentiment Analysis, Text mining, N-gram language models, Hidden Markov Models, Viterbi Algorithm, MEMMs, CRFs, Neural Language Models, Predict next word, LSTM,
perplexity computation, probabilities of tag sequence, language modelling, distributional semantics, Explicit-Implicit matrix factorization, Word2Vec, doc2vec, word analogies, sentence embeddings, topic modellings, training PLSA, machine translation, word alignment models, attention mechanism, dealing vocabulary, conversation Chat Bot, pointer generator networks, encoder-decoder architectures, intent classifier, slot tagger, NLU, task oriented dialog systems.
This course was taken by 20,000 members. Instructor from Google Brain team.
It covers word based encodings, how to use APIs, Text to sequence, Tokenizers, Padding, detect sarcasm, vectors, sarcasm classifiers, tokenized datasets, tensorflow datasets, subwords text encoders, Neural Networks, LSTM with codes, Convolutional Networks, Sequence models, word prediction, poetry, generating text using character based RNNs.
This course was taken by 42000 members. It covers, Regular Expressions, word tokenization, simple topic identification, named entity recognition, project: 'Building fake-news classifier', bag of words, introduction to gensim, Tf-idf with gensim, Tf-idf with wikipedia, spaCy NER, Multilingual NER with Polyglot, Count vectorizer, model inspection.
This course will cover why NLP is hard, linguistics, text similarity, part of speech, morphology and lexicon, morphological similarity, spelling similarity, NACLO, Thesaurus-based word similarity, Vector space model, dimensionality reduction, Syntax checking, Parsing, Earley Parser, Penn Treebank, prepositional phrase attachment, Statistical parsing, lexicalized parsing, dependency parsing, alternative parsing formalisms, Probabilities and Bayes theorem, word sense disambiguation, Noisy channel models, part of speech tagging, Hidden markov models, statistical POS tagging, Information extraction, Relation extraction, Question & Answering, Evaluation of Q&A architecture, Summarization, Sentence Simplification, collocations, Information retrieval, Text classification & clustering, Sentiment analysis, Representing and Understanding meaning, Inference, semantic parsing, Coherence, dialog systems, machine translation, Text generation.
This course was taken by 12000 members. It will cover, Bidirectional RNNs, Seq2Seq, Attention, attention theory, build a Chatbot, teacher forcing, memory networks.
NLP and Time Series course will cover: Work on GCP, Qwiklabs, linear models for sequence, modeling sequences with DNNs, RNNs to represent past, vanishing gradient descent, RNNs limits, introduces LSTM, GRUs,Time series prediction, Deep RNNs, Improving loss function, Text classification with native tensorflow, word embeddings, reusable embeddings, Encoder-Decoder models, Cloud poetry, AutoML, Tensor2Tensor, Dialogflow.
Leveraging IBM Watson's Natural Language Processing capabilities, you'll learn how to plan, implement, test, and deploy chatbots that delight your users, rather than frustrate them. True to our promise of not requiring any code, you'll learn how to visually create chatbots with Watson Assistant (formerly Watson Conversation) and how to deploy them on your own website through a handy WordPress plugin. Don't have a website? No worries, one will be provided to you. Chatbots are a hot topic in our industry and are about to go big. New jobs requiring this specific skill are being added every day, consultants demand premium rates, and the interest in chatbots is quickly exploding. Gartner predicts that by 2020, 85% of customer interactions with the enterprise will be through automated means (that's chatbots and related technologies). Here is your chance to learn this highly in demand set of skills with a gentle introduction to the topic that leaves no stone unturned. [Source: Courser.org]
This course covers, NLP, topic modeling, sentiment classification, Regex, ULMfit, Understanding RNNs, Word embeddings, Implementing a GRUs, Algorithm bias, Transformer introduction, Text generation.
This course was taken by 64000 members. It covers, Handling text in Python, Regular expressions, Regex with Pandas, basic NLP tasks, NLTK library, Naive Bayes classifier, Support Vector Machines, Text classifiers, Sentiment Analysis, Semantic, Generative models, LDA, Information Extraction, much more.
If you really like our article and is helping in your career, you can donate to support our effort.
You can donate, 1$, 5$, 10$ to PayPal.me/freemirrorneuron
Join our Facebook community of 75000+ members: facebook.com/groups/datasciencewithpython.
Youtube: youtube.com/c/mirrorneuron