A truly great course, focuses on the details you need, at a good pace, building up the foundations needed before relying more heavily on libraries an abstractions (which I assume will follow).
A neatly organized course introducing the students to basics of Processing text data, learning word embedding and most importantly on how to interpret the word embedding. Great Job!!
By Randall K•
By Teresa M B•
* some of the content is well-explained
* provides good solid knowledge about the background and implementation of common NLP tasks
* notebooks (and content generally) are unevenly distributed
* significantly stronger focus on ML, rather than on the NL side (this is consistent throughout the specialization)
* some of the explanations (e.g. in week 2) aren't clear
* specialization could be structured better -- word embeddings are introduced in course 1, but the in-depth discussion is here in week 4; would perhaps have made more sense to have that content build on itself
By J N B P•
In this course, you will learn to build an autocorrect model and different methods of building this model. The course felt a bit rushed with a lack of detailed explanation, students who are familiar with the concepts of NLP from before starting this specialization won't face any problem, but students who had just begun learning NLP through this specialization might feel a little difficult.
By Amlan C•
Too many gaps in the course. Many concepts not covered in the mathematical sense basic Grad. Desc. math would have been helpful. Also if you want to omit it totally you should have atleast one lab on how one would do it in real life using which library? Pytorch? Keras? What? Rest of the course is okay. Younous is great in explanation.
By Gent S•
The course material is good and you can learn new things, you can exercise python skills a lot as the assignments are quite long. However, the tutors are not the best in explaining the material as well as the videos are a bit vague. It would have helped if the tutors were a bit more experienced in teaching, but still overall good!
By Aditya J•
well I did deep learning specialization earlier things are mathematical, but here they don't go much into maths, and please make some concept chart, to link different algorithms.
By Chi Z•
BIg bug in week4's assignment! I don't know why not fix it. It turns out that I just train a dummy network
By Tanli H•
The instructors look like reading scripts and indeed a bit awkward.
By DHRUV M•
Topics were not clearly taught by instructure
By Nemish K•
This was an okay okay course
By Apoorv G•
Not much useful
By P G•
This course is unfortunately a waste of time. The lectures could be compressed into a 60 min video on basics of NLP with probabilistic models and uploaded to YouTube. You will feel initially like you learned a lot of things, yes, but then quickly forget this knowledge as everything is rushed and touched only superficially and you didn't develop solid understanding.
Also, the videos have to be revamped and recorded by someone a bit better in delivering lectures. The lecturer reads a script in a monotone voice and doesn't engage the learner. It feels like sitting through a boring slideshow at work rather than learning SOTA AI stuff from the world's leading tech institution...
This is just my personal opinion, perhaps it will work for you.
By Gennady S•
Too simple. The practical assignment is more not about learning embeddings, but about running about forward and backward pass on the shallow network.
By Abdullah A•
Do not waste your time, these very basic explanations of concepts barely teach you anything.
By Amit S•
Most of the algorithm and logic was implemented beforehand, I did not get to implement much, did not feel good after completing the 2 courses