Pros: Good selection of state of the art models (as of 2020). Also great lab exercises.

Cons: The video lectures and readings are not very helpful. Explanations about the more tricky parts of the models and training processes are vague and ambiguous (and some times kind of wrong?). You can find more detailed and easier to understand lectures on Youtube.

Have to say, the instructor didn't explain the concept well. A lot of explanation doesn't make sense, or just give the final logic and skip all the details. I need to search on youtube or google to understand the details and concept.

But, it covers state-of-art models for NLP. It's a good starting point and helped save time.

Although this course gives you understanding about the cutting edge NLP models it lacks details. It is hard to understand a structure of the complex NLP model during the few minute video. This course should have step by step explanations in the bigger number of lectures or increase their duration.

Low quality programming assignments, but considering the price it's good overall

In the previous 3 courses, the HW was a natural extention of the lectures and provided solid reinforcment of the course material. However, in this course, I found the courses did not prepare me for the HW. Furthermore, I found the lectures too terse, often incoherent, and the homework tried to introduce new concepts that were not discussed in the lectures. Also, the code in the labs was poorly organized and the lack of a consistent and coherent style between assignments and even previous courses, which made it difficult to follow the logic. I often spent a lot of time sorting out tensor indexing issues, which is very difficult in Jupyter without a debugger.

I think the last course is a bit rush... Many concepts are not natural and cannot be explained by one or two sentences. Comparing to the previous courses in the specialisation which really explains concepts and intuitions in detail, this last course is a bit too rough. I would rather spend another month to study the materials in two courses, instead of staying up late to read papers and blogs to understand what was not explained clearly in the course. And also, i see that trax is a good library but i think up to now it is not yet mature, and i really wish all the assignments can have tensorflow versions and let the students to choose.

This course is good if you want to be theoretically good with Transformers model. I mean now I can explain those concepts to my colleagues or pair. It lacks with the practical parts, a lot of exercises are too guided e there is no project that you can show off. The hugginface part is the most interesting for practicing but there are only a few lessons. In the end, do not expect to make a chatbot in week four, it is "just" a model that generates dialogue between two persons.

the homework is way too simplified esp. in week 3 and week 4. My impression is that the ungraded lab was actually the real homework but was put aside to allow more people to pass. That is not a good compromise.

Week 1 jumps into material that is better explained in Week 2. Attention deserves a more gradual and a more deep explanation. Weeks 3 and 4 cover a lot of ground, without going into depth.

Younes is a bad teacher. He may have good technical chops, but teaching is a different skill altogether. Overall, the NLP specialization design is much much worse compared with the DL Specialization. On one hand, you were taught a lot of stuff that are deep but cursory, on the other hand, the excises are either too difficult for you to get any clue or most of the time actually too simple and you only need to enter simple parameters, therefore cannot really learn anything! I really don't know why there are so many people giving 5 star rating!

Material coverage is very superficial. Do not expect to fully understand or be able to work with Attention models after doing this course.

Sadly, these types of courses and their fake near 5-star reviews are destroying Coursera.

Unfortunately, the classes are given at a very primitive level without explaining what exactly Attention models do. The programming exercises were not explained well, either

The course was pretty good. It introduced me to the state-of-the-art algorithms and techniques needed to have a sound understanding of NLP. One thing I didn't like about the teaching method in the whole specialization is that Younes was the one teaching the course content to us but Łukasz talked as if it was he giving some of the lectures, although we could clearly find out it's Younes from his voice. Thanks especially to Younes for doing all the hard work for the specialization. You deserve a 5 star.

A very good and detailed course. Definitely the most challenging course I have taken by DL.ai. Gives a good overview of Transformers, the current cutting-edge of NLP models. Also, provides great insight into Trax, Google Brain's ML framework, which was helpful in understanding how deep learning frameworks are built. One of the teachers is one of the authors of Trax!

Every week's assignment brings a new challenge and it was fun to complete the assignments. Course Instructors explain concepts very well. This course teaches you from the beginner level to a professional level. Covers every topic related to NLP. I enjoyed learning NLP with Deeplearning.ai. I would like to thank deeplearning.ai for making this course.

Good course in overall. The last two weeks' assignment is a little bit too light. The instructor could introduce more about loading pretrained models and fine-tune them as it is a popular practice nowadays for small companies with limited resources (data/computation). Introduction to "easy-to-use" framework such as huggingface is highly recommended.

This specialization covers from NLP basics to the advance models currently being used. All the programming assignments, contents and sessions were thoughtful. Exposure to Trax library and learning experience was really excellent. Thanks to the entire team of this specialization and coursera team.

The final weeks of this course, especially, introduce cutting edge NLP models and practices, such as T5, Huggingface and Reformer. This entire course was comprehensive in breadth. Highly recommended but you should be prepared to put 10x more hours into it than the Coursera estimates.

Thank you Coursera and the DeepLearning.AI team. The moment I set foot on this journey I did not think I would love NLP so much. The course is very informative: it teaches NLP from the very first naive algorithm to the State-of-the-art models today.

The course is so good and well presented. I really enjoyed the whole specialization. Thank you for this amazing course and the whole specialization which that me a lot. Thank you Andrew NG and deeplearning.ai team for this amazing specialization.

I learnt a lot about Transformers and Reformers which belong to the most advenced models for NLP tasks. The instructors were fully prepared though I'd prefer to see more animations in following courses. Thank you so much for spreading knowledge!

This course has helped me a lot in developing my NLP skills and now I am confident that I can solve NLP problems easily because both the instructors Younes and Luckerz has thought this course in a way that it can be absorbed in any NLP problem.

An excellent course that covers research that was published about two months early.

It doen't get more cutting edge than that, and the technology (reversible residual layers) is immediately applicable and a very powerful enabler.

Thanks a lot!

An amazing level of breadth and depth of the material presented. State of the art techniques are exemplified via carefully crafted lab assignments with sufficient hints for students to be able to comprehend hard technical concepts.

Thanks for setting out to do the impossible and creating this set of courses. You have opened a doorway to understanding where the state of the art is. The rest is up to me. That's the purpose of education.