In general, good. Misspellings in assignments is not very professional, should be revised.

Would be good if there are more checkpoints to see if the codes are correct or not.

but when it comes to text converting i am expecting more in model point of view

There should have been a little more elaboration in week 4 final content

Some example is hard to understand, and few of the diagram is ambiguous.

Especially later excercises contain code/instructions that are unclear

I would like to have more content and explanation about the math

I don't feel the assignments help understand the material.

The videos are too short. Discussions are oversimplified.

It is an interesting course to learn the basics of NLP

good for beginners, but needs more advanced concepts.

The explanations in the videos could be improved.

No longer required. Beyond my present knowledge.

Content is verbose and locks context in places

I believe that explanations where too shallow

very good course, a lot of stat and math

So many small mistakes here and there

Disappointed. need better syllabus

Mentor needed for the assignments!

I didn't quite get the feel of it

Problems in week 3 Assignment

Just ignore the video!

Too easy

Too easy

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!