Chevron Left
返回到 Natural Language Processing with Probabilistic Models

學生對 提供的 Natural Language Processing with Probabilistic Models 的評價和反饋

1,370 個評分


In Course 2 of the Natural Language Processing Specialization, you will: a) Create a simple auto-correct algorithm using minimum edit distance and dynamic programming, b) Apply the Viterbi Algorithm for part-of-speech (POS) tagging, which is vital for computational linguistics, c) Write a better auto-complete algorithm using an N-gram language model, and d) Write your own Word2Vec model that uses a neural network to compute word embeddings using a continuous bag-of-words model. By the end of this Specialization, you will have designed NLP applications that perform question-answering and sentiment analysis, created tools to translate languages and summarize text, and even built a chatbot! This Specialization is designed and taught by two experts in NLP, machine learning, and deep learning. Younes Bensouda Mourri is an Instructor of AI at Stanford University who also helped build the Deep Learning Specialization. Łukasz Kaiser is a Staff Research Scientist at Google Brain and the co-author of Tensorflow, the Tensor2Tensor and Trax libraries, and the Transformer paper....




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!!


226 - Natural Language Processing with Probabilistic Models 的 242 個評論(共 242 個)

創建者 Teresa M B



* some of the content is well-explained

* provides good solid knowledge about the background and implementation of common NLP tasks

less good:

* 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

創建者 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.

創建者 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.

創建者 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!

創建者 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.

創建者 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

創建者 Tanli H


The instructors look like reading scripts and indeed a bit awkward.



Topics were not clearly taught by instructure

創建者 Nemish K


This was an okay okay course

創建者 Amitrajit B


Doubt support can be better

創建者 Apoorv G


Not much useful

創建者 Darren


Generally good content, but there are several issues. The quizzes for each unit do not always reflect the material for the unit; they are obviously from other units within the course. Many of us have pointed this out on the course forums and reported the incorrect content, but it remains. There are also *lots* of typos and incorrect comments/text/captions in the videos. Some of them have pop-ups that point out the incorrect info, but many do not. The notation is inconsistent between slides in the course and differs even more between the slides and the assignments. It feels very sloppy. I have reported several of these, but no action has been taken. The creators seem to have created the course and walked away leaving a ton of errors and inconsistencies. There does not seem to be ongoing support for the course, even when there are clear, egregious errors.

創建者 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.

創建者 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.

創建者 Abdullah A


Do not waste your time, these very basic explanations of concepts barely teach you anything.

創建者 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

創建者 Rahul P


p​oor theory and the instructutor speaks fast. No lecture from lukaz