Course is good, not great - mainly let down by a few presentation issues, mistakes in slides and lab code, and a rather picky grader. This sounds worse then it is - there's only a few of each issue and in some ways it's a good test to see if you're paying attention :) Overall decent course to brush up on some NLP foundations, but you better have a good background in Linear Algebra if you don't want to take a large tangent.

I must admit that I am quite disappointed with this course. The explained material was interesting, but there were many errors in the assignments. It happens that people get 0 points for some exercises because of internal problems with the tests. In such cases, it is not even known what the problem is exactly. Hence you must do exercises exactly as the professors wanted, even if there are other approaches.

Not bad for beginners. Assignments are quite easy as they are almost done for you, however usefull to look carefilly at them to understand the idea behind.

I rated 3 stars as this course is not really about NLP, but more about other stuff. For example week 4 hashing tables exercise is interesting but not NLP related, more about efficient KNN finding

I found too many issues along with a lack of clarity in the programming assignments. Definitely needs to be refined.

The lectures are decent and the reading sections are nice, which displays the previous presentation contents.

The additional labs are just OK, not great. Some contain a lot of code that was not exactly clear so much of it was skipped.

I​ think it is an okay course for some basics. Most tasks are decent and well explained. Unfortunately there are quite a few inaccuracies that only sometimes get corrected and can lead to spending way more time on tasks than necessary, translating incorrect information on the slides into the correct ones or just simply be distracting.

Not sure of what I should master after this course. If it's the theory, or, say, the main principles, then OK : I have an idea of how NLP with vectors spaces works. But I feel totally unable to implement it, concretely. Perhaps it's not a problem if, in fact, we are just shown this technique as an initiation, before more complex ones.

Overall, the course covers a good content and informative but it lacks of in-depth discussion of each topics of NLP. It's not as thorough as Deep Learning Course. Also, the programming assignment is too picky about which functions of Python to be used while there are several ways to achieve the same outputs.

You guys need to work on the programming assignments, especially the teaching is below par as u guys didnt differentiate the word embedding we found by word by doc model which has to be a whole number and the embedding matrix which we generate from -1 to 1 which captures relationship between words.

I would like to have seen more breadth and depth in the course, and of course I have my perpetual beef with certain Coursera courses like this one that grade the programming assignments by looking for code features (which must be matched exactly) rather than evaluating results.

I feel like feed back and testing of your code code be more detailed to help pin point coding mistakes. I was spinning my wheels at the end and did see any solutions or discussions on my issues. I still passed but would like to see what I did wrong.

The lecture videos are a little short but provide some fundamental insights. It would be better if the videos were longer and more detailed or some supplemental resources. Overall a good course if you are a beginner or don't know where to start.

Shallow explanation in some topics in the lectures. It would be great if lecturer explained topics in more detail, and answer questions like why we use this model, show how it was created, pros and cons, and show why it works using math proofs.

I like the way the course use simple machine learning technic to solve a complicated problem,

for someone who likes mathematic a lot could be done in explaining mathematic concepts,

the assignment could be improved by using unit testing.

Andrew, come back with us!

Although very interesting, the course spend too many time and many student efforts in details like PCA and LSH. This is a good way to loss the big picture during the course.

Lectures were very straightforward and digestible, however the assignments had inconsistencies within themselves, especially between the written instructions and the comments in the code cells.

It's a very high level overview, I was expecting a bit more detail. The programming exercises are very basic, it felt like there could have been less but more advanced challenges to solve.

The topics were interesting overall and the lectures even though rather short were still rather informative. Too much focus on specificities of libraries and frameworks in the exams.

While this was a great introductory course to some of the basic tenets in NLP, various ancedotal examples were too convoluted to be useful in gaining an intuitive understanding

This course provides you with a good but basic start to the world of NLP. Week 4 LSH and Hashing should be explained more clearly. Assignments are not challenging.

Basically lecturers' delivery is not so good that you could get distracted easily.

Often, a video contents and a jupyter notebook don't match to each other.

Seemed easy to me. Rest all is good, the explanation and assignments.

I am reducing star by one rating because of the interface for assignment is poor.

Good coding part. For my background the lecture material was a bit too easy. However, if your intention was to keep it easy, then good job!

Liked the in-depth linear algebra and gradient descent, but missed some extras like lemmatization and HMMs in NLP...

C​ompared to other deeplearning.ai courses (esp. Adrew Ngs) very low in-depth explanations and challenge level.

Although the course presents an overview of the topic, I was expecting a more advanced and deeper approach.