Natural language processing (NLP) is a part of AI that studies how machines interact with human language. This emerging field is a popular field of study for AI and ML practitioners. Some leading universities of the world have courses available free of cost to get you started with the basic concepts of NLP and move to advanced levels.
Here, we look at some free courses that can get you started with NLP:
This video-based lecture series has 17 lessons, all being more than an hour long. This series equips the students with an introduction to cutting-edge research in deep learning applied to NLP. Word vector representations, dependency parsing, word window classification and neural networks, recurrent neural networks and language models, end-to-end models for speech processing and many more interesting topics will be some topics covered in this course.
This course from Coursera teaches you topics like language modelling and sequence tagging, vector space models of semantics, sequence to sequence tasks, and dialogue systems. One should take approximately 32 hours to complete this course. Familiarity with the basics of linear algebra and probability theory, machine learning setup, and deep neural networks is desired to get the maximum benefits from this course.
This course offered by Carnegie Mellon teaches ways to represent human languages as computational systems. It shows how to exploit those representations to write programs that do stuff with text and speech data like translation, summarisation, information extraction, natural interfaces to databases, and conversational agents. A prerequisite for the course is having knowledge of data structures and algorithms and good programming skills. The course brings you computational treatments of words, sounds, sentences, meanings, and conversations. There is a focus on rapid prototyping.
This is an advanced course on natural language processing. It focuses on advances in analysing and generating speech and text using recurrent neural networks. Applications of neural networks in NLP, with a focus on analysing latent dimensions in text, transcribing speech to text, translation between languages, and answering questions, are included in this course.
The subjects come in three high-level themes. This helps the students to progress from understanding the use of neural networks for sequential language modelling to comprehending their use as conditional language models for transduction tasks and then finally approaches employing these techniques in combination with other mechanisms for advanced applications. The course also discusses the practical implementation of such models on CPU and GPU hardware.
This video series will start with the basics of NLP through NLTK (Natural Language Toolkit). It will also teach frequency distribution which will show how to calculate, tabulate and plot the frequency distribution of words. Stemming, lemmatisation and tokenisation techniques will be covered as a part of this course. A requirement to pursue this course is knowledge of the basics of the Python programming language and any development environment to write Python programs. No prior knowledge of NLP techniques is assumed for this course.
This course carries a graduate-level introduction to NLP. It covers syntactic, semantic and discourse processing models with a focus on machine learning or corpus-based methods and algorithms. It will teach applications of these methods and models in syntactic parsing, information extraction, statistical machine translation, dialogue systems, and summarisation. One of the objectives of this course is to understand ML techniques used in NLP, which will include hidden Markov models and probabilistic context-free grammars, clustering and unsupervised methods, log-linear and discriminative models, as well as the EM (Expectation–maximisation) algorithm as applied within NLP.