This class is disappointing, especially after the Machine Learning Specialization classes which were given by Andrew Ng. Overall, this is the kind of class where the detailed syllabus the most valuable component. There is good information and topical introductions here, but I think the lecturer has forgotten the feeling of not being 1000% familiar with the material, especially the math.

Some notes:

1) Most, if not all topics are glossed over very quickly, especially mathematical ones. I very much miss Andrew's deeper (and more extensive) "intuition" videos here, and I say that as someone with a degree in computer science.

2) There are many errors in the lectures and in the labs. Sometimes a "popup" will tell you about them, sometimes not.

3) Popup quizzes in the lecture videos happen before the lecturer has even finished speaking about the topic being quizzed and are very jarring.

4) The "practice" (but still graded) quizzes have a difficulty level way out of proportion to the lecture content, especially those mathematical concepts that are so quickly glossed over. If you really must spend only 30 seconds on an equation and then expect us to remember/work it off the top of our head in a quiz days later, give us some exercises or some practice at least!

5) Labs are mostly just literal steps of "type this", "now type this". When it is more demanding, the instructions are not very useful and do not prepare anyone for the quirks of how libraries like numpy work. In many cases, there is no way to explain or diagnose why my numerical outputs were different from expected, especially when I followed all the instructions. Having to deep dive into the numpy documentation to find arbitrary arguments based on (seemingly arbitrary) data structure choices of the lab author in order to complete a lab doesn't feel productive or motivating.

6) Although a minor nit, the audio inconsistency between talking head and slides is very jarring. Compare to any of Andrew Ng's videos!

I believe the course does not allow you to study NLP in depth. Compared to the deep learning specialisation by deeplearning.ai, this course has probably hours(!) of video material less. PCA is for instance presented in ~4 minutes and the lecturer concludes with "now that you know all about PCA". The only further reference provided is a link to the standard textbook in the field, no detailed study guide or references for individual topics. Excercises are done in notebooks and test beginner python skills instead of nlp understanding (Basically: "Look up key i in dictionary j and store vector k"). It does do a good job in giving an overview about NLP.

I was torn between two and three stars. Two, as mathematics are dealt with far to shallow. No proofs, no motivation, nothing. And in the final week, there is a massive notebooks with a lot of flaws and a lot of cells you have to code in a specific, sometime suboptimal, way. Otherwise, the grader will throw errors. All in all, things are handled to shallow and it is more of a coding lesson than a deep dive into ML, which necessarily requires mathematics. This is one more of those "Become a data scientist without mathematics" things the world does not need.

lectures are pretty mediocure. basically it lacks motivation behind algorithms, you are simply told what to do, really like "machine" learning

you'll spend a lot of time in the assignment, not focusing on implementing your algorithm, but adjusting incorrect input or output format that passes all tests but fail the final grading for some reason (also in week 3 the assignment has one or two questions that do not even tell you what's the input data and you have to "print" them to get an idea lol)

The lectures skip over important features that should be explained in more detail. Other important concepts are left to the labs, even if those require a good explanation. Evaluations are not a help to practice or understand concepts. Most of the time spent on evaluations is figuring out how to do things in Python rather than follow the concepts. People can obtain 100% in the evaluations but learn nothing. It is indeed a very poor course.

Rather shallow and elementary course, I am disappointed. I did the deep learning specialization so I expected the same quality level here, but no it's not the case. In a way you're exploiting the fame of Andrew Ng to attract students, but Andrew is not teaching here and you're offering a content that is not up to expectations. I will try the following course and hopefully it will be more interesting.

The course covers some basic aspects of Natural Language Processing and can serve as an introduction to NLP, but it definitely not an in-depth course. The assignments are just some Python scripts where you have to fill in the gaps, which is not a helpful learning strategy, since you aren't given the opportunity to try things out by yourself and figure out what works.

There are too many errors in this course. The lecturing is uninspired. The assignments are boring and weak. Coming from many Andrew Ng courses and the Deep Learning Specialization, this is a huge disappointment. You had an opportunity to create an organization responsible for top tier tutorials and learning, and this level of commitment wastes that potential.

This particular course was not as good as other DeepLearning.AI courses are. This one was a bit non-intuitive and a lot of not so real life useful modules. Would be more interested in implementaion of applications, rather than building from scratch, because in real life implmentaion, we all are going to use libraries only.

The content is pretty nice, but the videos are so superficial. The assignments provide more theoretical background than the input sessions. There are many mistakes in the slides as well as in the assignments. I feel that this course is not mature yet.

The course runs through the important NLP topics at a very high level. It mostly explains the steps to solve problems using various methods, but an intuitive explanation of the techniques is missing.

The concept explanation is too weak in videos. The homework is too much focus on coding. The overall course lacks interactions between teachers and students , but I do learn some new stuff.

Exercises can be completed without the need to understand the methods. No flexibility in solving the programming assignments. Many small inconsistencies in the notebooks.

The course is very hurried without going into much details. It would be better if the instructors spend more time on the theory rather than skimming through codes.

Too superficial. Without DL specialization it could be too tough to understand what is takes place here. With it, everything is just too simple and flat.

Giving 2 stars because of notes provided with lectures, but there is a huge difference between what is taught in lectures and the real implementation

Mostly elementary feel-good with dinner recipe style follow-ups. Assignments are not set up well, have weird issues with submission error margins

Comparing it to other deeplearning.ai courses the content was harder to follow and the assignemnts were not super eucational.

Might be good for absolute beginners but if you have some background in maths or machine learning you won't find much new.

I want to skip this course because I don't enough background in the concept to be able to follow the lectures.

Not a great course, honestly. The videos are too shalow, and the exams involved completing functions.

Gets very confusing after week 2. The grammar used by the instructor is not very clear

I felt like the instructors are themselves a language model. Put in some style guys.

very help and the explanation is excellent .actually , i learn a lots things in nlp

Very confusing theory and labs comparing with previous Deep Learning track.