Great!

Thanks

Cool!!

bagus

fghrt

.....

grate

Great

Nice!

nice

Good

good

good

5*

no

bk

Having previously completed the Deep Learning Specialization, I came to this course with the intention of completing the whole NLP specialization, rather than because I was especially interested in the content of this first course from that specialization.

The Deep Learning Specialization sets a high standard of teaching quality and I have to say I found this course is not quite to the same standard. It's pretty good but not as good. The instructors are very knowledgeable, they make the effort to explain each topic clearly and they do a pretty good job of that.

What I felt could be improved is providing context of where each topic fits into the broader picture of both the theory and current practice of NLP. I was often left feeling, why are we spending time on this particular topic? Is this technique used in current practice or is it just of didactic or historical interest? Great teachers always have the broader context in mind and make sure that students see how everything fits into the bigger picture and why it is worth studying.

Although techniques were clearly explained, I felt that the underlying concepts were sometimes less well explained. An example is vector representations of words: we were shown the use of vector arithmetic to find analogies, but without much in the way of explanation of how this is possible. To me, this was the wrong way around: it makes more sense to me to first build an understanding of the representations, then introduce the remarkable result that these representations allow finding analogies.

In this course, sentences are represented as a "bag of words". This is processing natural language in the way a food processor processes food: chopping it up into a word soup. Since one of the most fundamental aspects of language is its structure, this might seem a hopeless approach. However it gives surprisingly good results for some simple tasks such as classifying tweets as having positive or negative sentiment. If you've done course 5 of the Deep Learning Specialization (Sequence Models), this will feel like a step backwards. There's no deep learning in this course. But I signed up for the course knowing that, so I can't criticise it on that basis. I'm taking the view that this course lays the foundations for more advanced and current topics in the subsequent courses in the specialization and I look forward to getting onto those.

The labs and assignments generally work smoothly. There are a few inconsistencies and a couple of the hints were a bit misleading but generally OK. It's a bit paint-by-numbers though, filling in bits of code within functions rather than working out for yourself how to structure the code.

This "Natural Language Processing with Classification and Vector Spaces" course covers: - Logistic regression - Laplacian smoothing, log likelihood, naive bayes models to predict sentiment of tweets - Euclidean distance, cosine similarity between word vectors to understand relationship between sets of text, and Principal Component Analysis - Language translation using rotation matrices, k-nearest neighbours and locality sensitive hashing The course has weekly lecture videos and has a summary reading after almost every video, which was especially helpful when trying to understand the concepts discussed in a video as a whole. There are also shorter labs to familiarise you with NLP concepts before the weekly graded programming assignment. Be sure to walk through and understand how the functions in utils_%.py accompanying each lab work. Similarly, walk through the functions in utils_%.py and how unit test cases are prepared in unittest.py accompanying each assignment. A good part of this course has been that the course team periodically releases new versions of the labs and assignments containing fixes or new approaches. Therefore bugs discovered by users in your assignment 3 months ago could already be fixed by the time you work on your assignment. The downside to the course is that the discussion forums were not actively monitored. Therefore there are some questions I have on certain concepts which were not answered by the time I completed the 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.

Took me roughly 5 days to finish this course. The course is of high quality. The instructors had done a great job preparing for the materials in this course. The videos are short and concise, and they focus more on intuition instead of mathematic details, which is great for beginners.

However, I would say the coding portion in this course is pretty limited. We did not get to write a lot of codes as most of the frameworks and functions had been implemented for us. What we need to do was simply filling in the blanks (and the comments will reveal the answers, making it even much easier). I also feel that some helper functions should not be provided. I think the course will be better if we get to write codes for labs also. Nevertheless, the course is open to the general public so I think this design is rational.

The course is interesting because it takes a look at NLP processing from a different view than just deep learning or word-in-bag type analysis. Most concepts are clearly explained, allowing most anyone with some python language experience to make it through the course. The programming assignments are similar to other courses. That is.... the assignments can be frustrating because you are trying to fill in the blanks through someone else's style of coding, but satisfying when the assignment is completed. I imagine that a few more iterations of the developing the course material and this will be another 5star course for the deeplearning.ai organization.

Every component was really informative to me. Besides, the mentors were always helpful and gave quick responses to my questions posed in the community forum. I was satisfied with most of the contents, because I got familiar with the vector representation of texts. However, the details of creating word embeddings were not described here in this specialization (maybe in another specialization such as NLP with Attention model). I want to know more about Google's BERT model, so I will take another course in the near future. Anyway, I would like to express my sincere gratitude to all the teachers and mentors of this specialization!

The course is a great introduction to NLP where various techniques and algorithms were explained clearly either through videos or notebooks. I'm giving 4 stars as some question in the quizzes had a bad formatting or couldn't submit the correct (answers are straightforward but still gives wrong answer as a non numerical entry). Another negative comment about some questions for example: can we use Kmeans to reduce the time of searching? and Kmeans was a wrong answer, though intuitavely it can be used as well. All in all, the course was great and I glad I took it.

This is a good intro-level NLP course. I don't regret taking it. I guess I just expected something a bit more challenging from Andrew Ng. Personally, I liked the assignments but I would like to see more materials (videos/readings) about the mathematical underpinnings of these methods. Then again, there are three more courses to go and something tells me, things will pick up. At the end of the day, the authors made the course very accessible to a broad audience. And if I really want more math, I suppose I can always read the original papers :)