Original article was published by Naina Chaturvedi on Artificial Intelligence on Medium
The Best Course for NLP with Deep Learning is Free
One of the most popular and acclaimed course…
Natural language processing (NLP), or NLP for short, is a branch of artificial intelligence that helps computers understand, interpret, and manipulate human language. It is broadly defined as the automatic manipulation of natural language, like speech and text, by software or technology. Natural language processing is a form of AI that is easy to understand and start using. It can also do a lot to help you in making better business decisions.
Some of the examples of NLP are :
- Spell check
- Voice text messaging
- Siri, Alexa, etc
Advantages of using NLP —
- Improve UX (user experience)
In order to make your website worth your user’s time, NLP can do help you a lot. Right from implementing features like spell check, autocomplete, to autocorrect in search bars, it makes it easy for users to navigate through the site effectively without losing interest. can make it easier for users to find the information they’re looking for, which in turn keeps them from navigating away from your site.
See how to build powerful UI/UX websites —
2. Chatbots — Automated support
Chatbots are trending. With chatbots, companies don’t need live agents to be the first point if communication. Information is fed and automated chatbots are able to help users navigate support articles and knowledge bases, order products or services, and manage accounts, help and support about the user’s queries.
3. Effective feedback Loop
For effective feedback, companies use various social media channels, reviews, contact forms, support tickets, etc. where the users or customers leave the feedback.
Using NLP, all the information can be assembled and turned into actionable insight that can help improve the product.
4. For Hiring best candidates
Natural language processing can help the company in sorting out the profile of the best candidates for a job. Using the same techniques as Google search, NLP automated tools scan applicant resume’s to extract people with the required background for a job.
Keeping all this in mind, there’s a brilliant course on NLP with Deep Learning offered by Stanford that people can take. Course self-description is written below (source: https://web.stanford.edu/)
Course Description —
Natural language processing (NLP) or computational linguistics is one of the most important technologies of the information age. Applications of NLP are everywhere because people communicate almost everything in language: web search, advertising, emails, customer service, language translation, virtual agents, medical reports, etc. In recent years, deep learning (or neural network) approaches have obtained very high performance across many different NLP tasks, using single end-to-end neural models that do not require traditional, task-specific feature engineering. In this course, students will gain a thorough introduction to cutting-edge research in Deep Learning for NLP. Through lectures, assignments, and a final project, students will learn the necessary skills to design, implement, and understand their own neural network models.
Prerequisites for this course —
- Proficiency in Python
- Intermediate level experience with Numpy and PyTorch
- Math — Calculus, Linear Algebra, derivatives, and understanding matrix/vector notation, and operations.
- Basic Probability and Statistics — basics of probabilities, gaussian distributions, mean, standard deviation, etc.
- Foundations of Machine Learning
Coursework structure —
Assignments constitute 54% of the coursework while Final Project 43%.
There are five assignments (source: https://web.stanford.edu/ ) —
- Assignment 1 (6%): Introduction to word vectors
- Assignment 2 (12%): Derivatives and implementation of word2vec algorithm
- Assignment 3 (12%): Dependency parsing and neural network foundations
- Assignment 4 (12%): Neural Machine Translation with sequence-to-sequence and attention
- Assignment 5 (12%): Neural Machine Translation with ConvNets and subword modeling
The final project consists of —
- Project proposal (5%)
- Project milestone (5%)
- Project poster/video (3%)
- Project report (30%)
The course is taught by the renowned academic, researcher, and author Christopher Manning, along with head Teaching Assistant Matthew Lamm, with Amelie Byun as the course coordinator, and a group of teaching assistants.
Where to access the videos?
You can access the lecture videos here —
My feedback —
This is one of the best course I have completed and it gave me a thorough understanding of word vectors, word window classification, Matrix Calculus, and Backpropagation, Neural Network and PyTorch, Recurrent Neural Networks and Language Models, Vanishing Gradients and Fancy RNNs, Machine Translation, Seq2Seq, ConvNets for NLP.