Chevron Left
返回到 Natural Language Processing with Sequence Models

學生對 deeplearning.ai 提供的 Natural Language Processing with Sequence Models 的評價和反饋

4.5
893 個評分
180 條評論

課程概述

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....

熱門審閱

SA

2020年9月27日

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

2021年11月11日

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.

篩選依據:

101 - Natural Language Processing with Sequence Models 的 125 個評論(共 188 個)

創建者 Vladimir B

2020年7月29日

Great course! I loved it.

創建者 Divya S

2021年9月19日

I​ loved this course :)

創建者 Mario A C F

2021年6月26日

A​mazing Experience!

創建者 Esakki p E

2021年5月21日

Best place to learn

創建者 yeha

2020年9月16日

can't wait course 4

創建者 Balaji V

2021年2月20日

Excellent Content!

創建者 Kushagra P

2022年3月11日

Execellent course

創建者 Deleted A

2020年9月5日

Very useful !!!!

創建者 Mohammad B A

2020年12月27日

I am so happy

創建者 Jyotin P

2020年11月20日

Amazing course

創建者 Sohail Z

2020年9月7日

JUST GREAT!!!

創建者 Jose L L d J S

2021年9月17日

E​xcellent!

創建者 larawang

2022年5月7日

Thank you!

創建者 Chen

2021年10月27日

Thank you!

創建者 Onuigwe V

2020年8月29日

Excellence

創建者 Zoizou A

2020年10月25日

amazing

創建者 Yongxin W

2020年10月2日

so cool

創建者 Rifat R

2020年9月23日

Awesome

創建者 Jeff D

2020年11月15日

Thanks

創建者 MOURAD B

2021年4月22日

goood

創建者 Ricardo F

2021年1月15日

Grear

創建者 M n n

2020年11月22日

Nice

創建者 Saoudi H

2020年9月27日

good

創建者 Dave J

2021年2月15日

There are lots of good points. The instructors are knowledgeable, Lukasz Kaiser is one of the authors of Tensorflow and Trax. The material is generally presented in a clear way. The labs and assignments work smoothly. You learn how to implement significant NLP tasks in a modern framework (Trax).

There are areas where I felt the course could have been better.

The amount of taught material is only about half an hour of lecture per week. I felt that it covered the bare minimum to get you through the assignments but I would have liked a lot more content, going in more depth into the concepts and how the performance of the models discussed compares to state-of the-art models and how it could be improved.

Having already done the Deep Learning Specialization, I was disappointed that this course did not build on that as a foundation. There is a lot of overlap between this course and course 5 of the DL Specialization, Sequence Models. To me, it would have made more sense to make that course a prerequisite, thus avoiding all the duplicated material and instead going beyond it.

The other area where there's some room for improvement, though it's not at all bad, is the teaching style, which is mostly reading from a script. I would like to see more effort to engage with the learner and think about what they might need to progress on their learning journey. For example, discuss the strengths and weaknesses of an approach and where it fits into the history and state of the art of the subject; anticipate questions or likely misunderstandings and try to cover them or point to supplementary material.

Overall, a good course that could have been a great course.