Again this course was pretty fast (I'm starting to feel like all four courses together are about the length of one standard course). One downside is there are not graded programming exercises like in the Convolutional Neural Networks course. I learned how to use the text processing tools in the keras API. Also was cool to see how effective the stacked LSTM models are.

Very detailed step by step tutorials of using Tensorflow with lots of effort to make things as easy to understand as possible. The use cases also quite interesting. A little lack of theory comparing to other courses by deeplearning.ai. Quizzes are quite undeveloped. But that is understandable, because the main goal of the course to introduce Tensoflow.

Gives you a nice overall understanding of what NLP is. There are notebooks to play with concepts. However, this course dials down on the practical aspect (and the theoretical one) even more than the previous course. I think the students will benefit more if more ground is covered on the theoretical aspect of RNNs, LSTMs, and GRUs. Nice course overall.

Like the other courses, this course is very good. It's very hands-on, which is good. However, unlike the previous courses, this course exercises are more like fully completed Colab Notebooks, which we can only run ou change some things. In the previous courses, the notebooks had more exercises, questions and variety. But it's a good course anyway.

This course is very interesting BUT there is no responsible person in the discussion to answer people who ask. (that's why I give only 4 stars)

It's good to add some resume after the course about the name of function and argument end things like that, this will help people who hate to return always to the documentation always.

And thank you.

This course provided a nice survey of some of the NLP techniques that can be brought to bear to make sense of language. It was a nice touch that we got a peek at one way that one might produce language (reversing some of the techniques to make sense of language).

While not state of the art, this is a good intro into the field!

A fantastic way of explaining things. Used a number of datasets to introduced different situations. However, it contains some drawbacks. For example, maybe the notebook is written using old API, hence the data are needed to be wrapped using `np.array()`. Again, It would be better if the notebooks are graded too.

This course should included other Neural methods for NLP to practice in tensorflow and the excercises should be a bit more difficult, they were way too easy to deal with. Assignments help a lot in getting hands on experience. The course overall, gave a nice and concise overview of the tensorflow framework.

Enjoyed the course, more content that the other lessons in the series. Still lacks notes and direct codes to save and practice on our own rather using the google colab that could be in the future require subscription. Good explanations can't wait to start the last course on the series.

Unfortunately the exercises in this course are all ungraded, they don't really have a benchmark goal (in contrast to the earlier courses in the specialization). You're still able to work with 'ungraded' assignments but the difficulty level seems a bit lower.

More intuition for different choices of hyperparameters (layer types, layer specifications) would have been great.

Named Entity Recognition is one of the most important NLP tasks in the Industry, but it is completely missing.

Transformers are missing.

I'm not as satisfied with this course as I am with CNN or Intro to TensorFlow, main reason being there was no graded exercise materials unlike the other two above mentioned ones. I still loved the videos nonetheless. Thanks Laurence and Andrew :)

I'm missing the programming assignments as in earlier courses also i also felt a lack in links of google notebook and we only have videos of the programs working rather than getting hands on with links to corresponding google colab notebooks.

More info might be provided especially on creating model architecture. I mean in hyperparameter tuning side should be more clarified. What happened when we change emdedding dimension is important to understand whole logic as an example.

Extremely interesting field and am super excited to experience the Tensorflow libraries where so much (of code, which I used to write in raw python, years ago !) is encapsulated in simple, ready-to-consume, yet powerful modules.

At first I though the courses paid too much attention on data preprocessing when implementing NLP.

Well, how to figure out the right way to deal with natural language is what we should learn in this course and it really helps!

This complete course provides you with a great welcome journey in the world of NLP. Laurence really provided the basics required to understand the topics. Additionally, it was fun to listen to a talk of Andrew & Lawrence.

A good course for NLP, but I like the previous courses more. This course does not deliver the teachings as clear as the previous courses. And I can feel that we've skipped a lot of things in this course.

These classes are excelling practical examples of how to use tensorflow for various problem types. My only objection is they are slightly light on the actual, behind the scenes, math and intuition.

The course is great, but the assignments were not designed as well as the ones in the previous courses. I believe that a careful design of the assignments could significant improve the experience.

Was really easy as compared to CNNs. I wish this had more notebook evaluations like the course for CNNs since that really made me feel good overcoming all the tasks, especially the last one.

Good course that gives you basic understanding of word embeddings, sequence analysis, and many other things. Thank you for Mr. Moroney and the entire Coursera team for making it available.

NLP is a very interesting topic, and this course brings me closer to actually working on a NLP project myself. I don't know why exactly, but I cannot be fully satisfied with this course.

A good course which gave a in depth overview of NLP classes in tensorflow . Need to include more challenging assignments and also should bring in modules on BERT which is SOTA.

Excellent course but I would have liked to have exercises that required coding. I learn better by writing code, figuring out the order, etc. Still, a very good course.