Thank you!

Thank you!

Excellence

Excelent!

Very Good

All good.

Brutal.

Awesome

amazing

so cool

Awesome

Thanks

goood

Grear

good

Good

Nice

good

There are lots of good points. The instructors are knowledgeable, Lukasz Kaiser is one of the authors of Tensorflow and Trax. The material is generally presented in a clear way. The labs and assignments work smoothly. You learn how to implement significant NLP tasks in a modern framework (Trax).

There are areas where I felt the course could have been better.

The amount of taught material is only about half an hour of lecture per week. I felt that it covered the bare minimum to get you through the assignments but I would have liked a lot more content, going in more depth into the concepts and how the performance of the models discussed compares to state-of the-art models and how it could be improved.

Having already done the Deep Learning Specialization, I was disappointed that this course did not build on that as a foundation. There is a lot of overlap between this course and course 5 of the DL Specialization, Sequence Models. To me, it would have made more sense to make that course a prerequisite, thus avoiding all the duplicated material and instead going beyond it.

The other area where there's some room for improvement, though it's not at all bad, is the teaching style, which is mostly reading from a script. I would like to see more effort to engage with the learner and think about what they might need to progress on their learning journey. For example, discuss the strengths and weaknesses of an approach and where it fits into the history and state of the art of the subject; anticipate questions or likely misunderstandings and try to cover them or point to supplementary material.

Overall, a good course that could have been a great course.

I'm a master/graduate student who took an NLP course in Uni.

I think that overall this is a very a good introduction to the topic. Some concepts are really well explained - in a simple manner and with a lot of jupyter-lab code to experiment with.

In general in this specialization - the first 3 courses are good. There are some quirks (e.g. why Lukas is needed at all? He doesn't really teaches, just passes it on to Younes) but nevertheless I learned from it. And I think they have good value in them.

The 4th one, however, is completely disappointing. First 2 "weeks" are confusing, not really well explained, but somewhat "bearable". The last 2 weeks are complete sham. They claim to teach "BERT" and "T5" but don't really give any value. You're better off going elsewhere to learn these concepts.

If it wasn't for this, I would give the overall experience a 5 stars, but because of this, I think the overall is more like 3 or 4.

The courses have really enlightened me on NLP. I had no idea about the techniques. I'll give it 4 stars, because the course instructors have a monotonicity of lecturing as if reading from a teleprompter with a fake synthetic voice. It sometimes gives me a headache and I end up muting the videos and just reading the subtitles (which a lot of times don't make sense and are short paces so I have to freeze the screen, and open 2 other windows and read the lower caption text). I have been doing many courses on this platforms, and even though the instructors are on the top of their fields, but the way they deliver the courses is just "sometimes" and "not always" painful. I am sure this is not how they teach there own classes, especially in Stanford. Even though the course is 50$ per month, a think it won't cost the instructors much to show some authentic enthusiasm.

The course is quite informative and it focuses on some cutting edge developments in NLP, which is great. I also really appreciated how well the instructors managed to explain the important concepts of GRU and LSTM. However, I wish the assignments were a bit more challenging. Most of the time, they felt like step-by-step instructions that are almost impossible to get wrong, with not much room for imagination. Good for self-esteem, not so good for skill building... Still, this was by no means a waste of time. A good foundational course that leaves you hungry for more. So perhaps it was the instructors' intention all alone to make it this way :)

Better then the first two courses. Excellent week 1 introduction to Trax - I especially enjoyed Lukasz video about the origins, along with the links to source code and extra readings. Much of the technical content in weeks 2-4 is better covered in the deep learning specialization, however it's fairly brief and demonstrated using Trax so I still learnt something new. The applications in the assignments are interesting - the comparison between RNNs and n-gram models when doing text generation, parts of speech tagging and the question answer duplicate detection with Siamese models. Also got to try a few new things with numpy which was nice.

To begin with, the course is very well structured and the assignments make you apply the theory what you have learnt in the videos in an effective way. The community on slack is very helpful if you need any help. The only thing that I didn't like was the course assignments were using *trax* for building the models instead of powerful frameworks like tensorflow, pytorch. That's the only reason I am rating 4 instead of 5 stars. Overall it is a pretty nice course and you will find it very easy if you have completed the Sequence models course from Andrew Ng's Deep learning specialization.

This is a great course for natural language processing ! The video is short buy very precise for the concept. I think this is a middle level course, so one should already have the basic knowledge of deep neural network, and python skill. Then you will enjoy this journey. I hope for a more freedom style in coding assignment, rather than fill in the None parts style. Then we could obtain a solid knowledge by the deep practice. All in all, this is a great NLP course !!!