Natural Language Processing (NLP) has made several ground-breaking achievements in the past couple of years. In the current scenario, almost all organisations use this technique to bring about human-like conversation capabilities in machines, among other applications.
As the concept’s popularity is growing, many courses are offering machine learning enthusiasts to take a deep dive and understand this technique from scratch. Here we list eight top-rated Natural Language Processing (NLP) MOOCs to learn the concepts from.
Note: The list is in no particular order
Natural Language Processing Specialisation
Rating: 4.6
Source: Coursera
About: Two experts in machine learning and natural language processing teach this course — Younes Bensouda Mourri, who is an Instructor of AI at Stanford University and Łukasz Kaiser, who is a Staff Research Scientist at Google Brain, and the co-author of TensorFlow, Tensor2Tensor and Trax libraries, and the Transformer paper. By the end of this Specialisation course, you will be able to design natural language processing applications that can perform question-answering and sentiment analysis, create tools to translate languages, summarise text, build chatbots, and more.
Know more here.
Natural Language Processing with Deep Learning
Source: Stanford University
About: In this course, you will study the fundamental concepts of natural language processing and its part in current and emerging technologies. You will obtain an understanding of modern neural net algorithms for the processing of linguistic information. You will also learn topics like word vectors, neural networks, dependency parsing, language models and RNNs, vanishing gradients, translation, and more.
Know more here.
Applied Natural Language Processing
Rating: 386 stars on GitHub
Source: UC Berkeley
About: This course is provided by the University of California, Berkeley that examines the use of natural language processing as a set of methods for exploring and reasoning text as data, focusing especially on the applied side of NLP. The topics include text-driven forecasting and prediction, features derived from low-dimensional representations of words, sentences, and documents, exploring textual similarity for the purpose of clustering, information extraction (extracting relations between entities mentioned in the text), among others.
Know more here.
Natural Language Processing with Probabilistic Models
Rating: 4.8
Source: Coursera
About: This is an intermediate course, where you will learn to create a simple auto-correct algorithm using minimum edit distance and dynamic programming, apply the Viterbi Algorithm for part-of-speech (POS) tagging, which is essential for computational linguistics, and more. The course also covers writing an auto-complete algorithm using an N-gram language model. This specialisation is designed and taught by Younes Bensouda Mourri, and Łukasz Kaiser, who have also designed the above-mentioned course on Natural Language Processing Specialisation.
Know more here.
A Code-First Introduction to Natural Language Processing
Rating: 2.6k stars on GitHub
Source: Fast.ai
About: This course which was originally taught at the the University of San Francisco’s Masters of Science in Data Science program, is a code-first introduction to NLP in Python with Jupyter Notebooks, using libraries such as sklearn, NLTK, PyTorch, and fastai. The applications covered in this course include classification, topic and language modelling as well as translation. The course illustrates a blend of traditional natural language processing topics like regex, SVD, Naive Bayes, etc. including some of the recent neural network approaches, such as RNNs, seq2seq, transformer architecture, etc.
Know more here.
Natural Language Processing
Rating:
Source: University of Washington
About: In this course by the University of Washington, you will learn various exciting topics like language models, Hidden Markov Models, Dependency Grammars, Structural Graphical Models, Neural Networks, and more. The source provides slides as well as notes in PDFs, which make it easy for the learners to understand each topic precisely.
Know more here.
NLP: Twitter Sentiment Analysis
Rating: 4.7
Source: Coursera
About: NLP: Twitter Sentiment Analysis is a hands-on project, where you will train a Naive Bayes classifier to predict sentiment from thousands of Twitter tweets. It covers step by step process to import libraries and datasets, perform Exploratory Data Analysis, perform data cleaning, remove punctuation, create a pipeline to remove stop-words, punctuation, perform tokenisation and more such tasks.
Know more here.
Deep Learning: Advanced NLP and RNNs
Rating: 4.7
Source: Udemy
About: In this course, you will learn how to build a text classification system (can be used for spam detection, sentiment analysis, and similar problems), build a neural machine translation system (can also be used for chatbots and question answering), create a sequence-to-sequence (seq2seq) model and more. The topics include bidirectional RNNs, seq2seq (sequence-to-sequence), attention, memory networks, and other such.
Know more here.
