Chevron Left
返回到 Natural Language Processing with Sequence Models

学生对 deeplearning.ai 提供的 Natural Language Processing with Sequence Models 的评价和反馈

4.5
895 个评分
180 条评论

课程概述

In Course 3 of the Natural Language Processing Specialization, you will: a) Train a neural network with GLoVe word embeddings to perform sentiment analysis of tweets, b) Generate synthetic Shakespeare text using a Gated Recurrent Unit (GRU) language model, c) Train a recurrent neural network to perform named entity recognition (NER) using LSTMs with linear layers, and d) Use so-called ‘Siamese’ LSTM models to compare questions in a corpus and identify those that are worded differently but have the same meaning. 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....

热门审阅

SA

Sep 27, 2020

Overall it was great a course. A little bit weak in theory. I think for practical purposes whatever was sufficient. The detection of Question duplication was a very much cool model. I enjoy it a lot.

AU

Nov 11, 2021

This is the third course of NLP Specialization. This was a great course and the instructors was amazing. I really learned and understand everything they thought like LSTM, GRU, Siamese Networks etc.

筛选依据:

126 - Natural Language Processing with Sequence Models 的 150 个评论(共 188 个)

创建者 D. R

Mar 22, 2021

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.

创建者 Kostyantyn B

Nov 15, 2020

The course is quite informative and it focuses on some cutting edge developments in NLP, which is great. I also really appreciated how well the instructors managed to explain the important concepts of GRU and LSTM. However, I wish the assignments were a bit more challenging. Most of the time, they felt like step-by-step instructions that are almost impossible to get wrong, with not much room for imagination. Good for self-esteem, not so good for skill building... Still, this was by no means a waste of time. A good foundational course that leaves you hungry for more. So perhaps it was the instructors' intention all alone to make it this way :)

创建者 Laurence G

Mar 22, 2021

Better then the first two courses. Excellent week 1 introduction to Trax - I especially enjoyed Lukasz video about the origins, along with the links to source code and extra readings. Much of the technical content in weeks 2-4 is better covered in the deep learning specialization, however it's fairly brief and demonstrated using Trax so I still learnt something new. The applications in the assignments are interesting - the comparison between RNNs and n-gram models when doing text generation, parts of speech tagging and the question answer duplicate detection with Siamese models. Also got to try a few new things with numpy which was nice.

创建者 Saurabh D

Aug 11, 2020

To begin with, the course is very well structured and the assignments make you apply the theory what you have learnt in the videos in an effective way. The community on slack is very helpful if you need any help. The only thing that I didn't like was the course assignments were using *trax* for building the models instead of powerful frameworks like tensorflow, pytorch. That's the only reason I am rating 4 instead of 5 stars. Overall it is a pretty nice course and you will find it very easy if you have completed the Sequence models course from Andrew Ng's Deep learning specialization.

创建者 Feng J

Feb 7, 2021

This is a great course for natural language processing ! The video is short buy very precise for the concept. I think this is a middle level course, so one should already have the basic knowledge of deep neural network, and python skill. Then you will enjoy this journey. I hope for a more freedom style in coding assignment, rather than fill in the None parts style. Then we could obtain a solid knowledge by the deep practice. All in all, this is a great NLP course !!!

创建者 Galangkangin g

Aug 7, 2021

Material was good, but the assignments were too hand-holding. We were told what to do on every step of the algorithm. I think it's better to give an almost empty signature function and describe what we should create for that function (input/output) so we can gain more understanding

创建者 Oleksandr P

Apr 4, 2021

This course is good but it is too short in my opinion. It is sometimes hard to wrap your head around some concepts that are describe in a 5 minute video. I think this course should have more video lectures with a more detailed (step by step) explanations.

创建者 Pradeep B

Aug 28, 2021

The topics are definitely advanced however the content is very basic and is meant for beginners if I am not wrong. If one is 'starting' to learn to apply deep learning via trax to sequence models, then this is the best course for that goal.

创建者 Ahnaf A K

Aug 6, 2020

It was a bit repetitive of the 'Sequence Model' course from the Deep Learning specialization, only with the exception of implementing in TRAX.

创建者 Nishank L

Nov 14, 2021

Assignments are good. Can we have these using pytorch. Or better: Can a person choose his own language and build entire code on that !!

创建者 Osama A O

Oct 19, 2020

Great course, although would have been better if assignments were implemented in Keras or PyTorch. Otherwise, definitely worth it!

创建者 Matthew P

Jan 7, 2021

Great information, but some of the assignments had errors and there weren't many interactions from the TAs on the Slack or Forum

创建者 Marc G

Feb 10, 2022

Great course! I would have liked Keras/TensorFlow 2.x or Pytorch to be used instead of Trax which is not as frequently used.

创建者 Manuela D

Mar 14, 2022

Interesting and well explained altough assignment excercise are difficult to understand and they are just focus on Trax

创建者 Mohsen A F

Oct 24, 2020

The clarity of exposition was superb! 1 star less for using TRAX. I would have rathered to use Keras or Tensorflow.

创建者 Saurabh K

May 24, 2021

We might have included little bit more details on dimensions of the inputs and outputs of the Sequence models.

创建者 Mridul G

Jul 14, 2021

T​he course is very good, but its not complete in itself. The way course was taken and everything is good.

创建者 Hair P

Nov 20, 2020

Overall the content was great. Please make sure that errors in the notebooks are corrected.

创建者 RAHUL K

Sep 18, 2020

The course is designed quite well to boost understanding of Sequence Models in great depth

创建者 Steve H

Apr 3, 2021

Excellent course, but probably worth doing the deep learning specialisation first!

创建者 Ke Z

Feb 24, 2021

I dont like to use TRAX. If it is using tensorflow, then I will give 5 stars

创建者 Alireza S

Dec 11, 2021

I prefer that the lecturer using TensorFlow instead of Trax for exercises

创建者 kerolos E

Mar 23, 2022

Almost perfect. More Explanation in implementation is needed.

创建者 Vitalii S

Jan 21, 2021

Good information, but some assignments were an embarrassment.

创建者 Nikita M

Dec 7, 2020

Not as good as original courses by Andrew