About this course: This course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few. Upon completing, you will be able to recognize NLP tasks in your day-to-day work, propose approaches, and judge what techniques are likely to work well. The final project is devoted to one of the most hot topics in today’s NLP. You will build your own conversational chat-bot that will assist with search on StackOverflow website. The project will be based on practical assignments of the course, that will give you hands-on experience with such tasks as text classification, named entities recognition, and duplicates detection. Throughout the lectures, we will aim at finding a balance between traditional and deep learning techniques in NLP and cover them in parallel. For example, we will discuss word alignment models in machine translation and see how similar it is to attention mechanism in encoder-decoder neural networks. Core techniques are not treated as black boxes. On the contrary, you will get in-depth understanding of what’s happening inside. To succeed in that, we expect your familiarity with the basics of linear algebra and probability theory, machine learning setup, and deep neural networks. Some materials are based on one-month-old papers and introduce you to the very state-of-the-art in NLP research.
Who is this class for: This course is for those who are interested in NLP field and want to know the current state-of-the-art in research and production. We expect that you have already taken some courses on machine learning and deep learning, but probably have never applied those models to texts and want to get a quick start.
Taught by: Anna Potapenko, Researcher
HSE Faculty of Computer Science
Taught by: Alexey Zobnin, Accosiate professor
HSE Faculty of Computer Science
Taught by: Anna Kozlova, Team Lead
Yandex
Taught by: Sergey Yudin, Analyst-developer
Yandex
Taught by: Andrei Zimovnov, Senior Lecturer
HSE Faculty of Computer Science
| Basic Info | Course 6 of 7 in the Advanced Machine Learning Specialization |
| Level | Advanced |
| Commitment | 5 weeks of study, 4-5 hours per week |
| Language | English |
| How To Pass | Pass all graded assignments to complete the course. |
| User Ratings |
- Reading: Prerequisites check-list
- Video: Welcome video
- Video: Main approaches in NLP
- Video: Brief overview of the next weeks
- Video: [Optional] Linguistic knowledge in NLP
- Video: Text preprocessing
- Video: Feature extraction from text
- Video: Linear models for sentiment analysis
- Video: Hashing trick in spam filtering
- Reading: Getting started with practical assignments
- Video: Neural networks for words
- Video: Neural networks for characters
- Video: Perplexity: is our model surprised with a real text?
- Video: Smoothing: what if we see new n-grams?
- Reading: Perplexity computation
- Video: Hidden Markov Models
- Video: Viterbi algorithm: what are the most probable tags?
- Video: MEMMs, CRFs and other sequential models for Named Entity Recognition
- Reading: Probabilities of tag sequences in HMMs
- Video: Neural Language Models
- Video: Whether you need to predict a next word or a label - LSTM is here to help!
- Video: Explicit and implicit matrix factorization
- Video: Word2vec and doc2vec (and how to evaluate them)
- Video: Word analogies without magic: king – man + woman != queen
- Video: Why words? From character to sentence embeddings
- Video: Topic modeling: a way to navigate through text collections
- Video: How to train PLSA?
- Video: The zoo of topic models
- Video: Noisy channel: said in English, received in French
- Video: Word Alignment Models
- Video: Encoder-decoder architecture
- Video: Attention mechanism
- Video: How to deal with a vocabulary?
- Video: How to implement a conversational chat-bot?
- Video: Sequence to sequence learning: one-size fits all?
- Video: Get to the point! Summarization with pointer-generator networks
- Video: Intent classifier and slot tagger (NLU)
- Video: Adding context to NLU
- Video: Adding lexicon to NLU
- Video: State tracking in DM
- Video: Policy optimisation in DM
- Video: Final remarks
- Reading: Keep up-to-date with NLP research
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
| Purchase Course | |
|---|---|
| Access to course materials | Available |
| Access to graded materials | Available |
| Receive a final grade | Available |
| Earn a shareable Course Certificate | Available |
nicely organized! amazing course. I am doing my PHD in NLP, and I had prior NLP classes in coursera, but I still can learn quite a lot knew things from this course. It gives NLP from another perspective, and it is really up-to-date with deep learning and tensor flow. Love such classes. Hope there are more classes offered from these instructors.
Nice introduction and very practical
The course covers traditional statistical techniques as well as some latest deep network methods, and gladly both the instructors speak good English on the course of Natural Language Processing :-) . The assignments of this course are also more guided and easier to follow than the previous courses of the specialization, meanwhile it will require quite a bit of environment setup efforts like docker and server to finish some assignments. Having access to some GPU machine/environment is recommended to speed up the training/testing process.
AS
Very good course!! A big thanks to all the instructors. However I feel the course covered a lot of stuff which affected its focus. May be it would have been better to focus on fewer techniques but in greater detail both in theory and assignments.