Chevron Left
Volver a Procesamiento de lenguajes naturales

Opiniones y comentarios de aprendices correspondientes a Procesamiento de lenguajes naturales por parte de HSE University

4.5
estrellas
801 calificaciones
204 reseña

Acerca del Curso

This online course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few. Upon completing, you will be able to recognize NLP tasks in your day-to-day work, propose approaches, and judge what techniques are likely to work well. The final project is devoted to one of the most hot topics in today’s NLP. You will build your own conversational chat-bot that will assist with search on StackOverflow website. The project will be based on practical assignments of the course, that will give you hands-on experience with such tasks as text classification, named entities recognition, and duplicates detection. Throughout the lectures, we will aim at finding a balance between traditional and deep learning techniques in NLP and cover them in parallel. For example, we will discuss word alignment models in machine translation and see how similar it is to the attention mechanism in encoder-decoder neural networks. Core techniques are not treated as black boxes. On the contrary, you will get in-depth understanding of what’s happening inside. To succeed in that, we expect your familiarity with the basics of linear algebra and probability theory, machine learning setup, and deep neural networks. Some materials are based on one-month-old papers and introduce you to the very state-of-the-art in NLP research. Do you have technical problems? Write to us: coursera@hse.ru....

Principales reseñas

GY
23 de mar. de 2018

Great thanks to this amazing course! I learned a lot on state-to-art natural language processing techniques! Really like your awesome programming assignments! See you HSE guys in next class!

DW
2 de ago. de 2020

It's a comprehensive course on NLP. The instructors clearly explain both the traditional/classical approaches and modern approaches such as neural networks in NLP.

Filtrar por:

151 - 175 de 204 revisiones para Procesamiento de lenguajes naturales

por Laura C

31 de mar. de 2020

Good job!

por haiya1994

9 de oct. de 2018

very good

por 过群

7 de mar. de 2018

OMG!!!!!

por Rifat R

13 de may. de 2020

Awesome

por Владимир В

25 de feb. de 2019

super!

por Krishna H

21 de ago. de 2020

Good!

por 4NM18CS094 M S R

18 de sep. de 2021

GOOD

por Joe W

9 de ene. de 2020

Amazing course!! This course introduces both classical and deep learning approaches in NLP and discusses the connection between the two. The homework is generally very well designed. The final project requires deployment in production which is a nice experience to have for real world application even though I was hoping for more in-depth model building based on the materials in the tutorials (perhaps this is covered in the honors project). One recommendation is to update the materials to include BERT, ELMO and transformers from the last two years. I know it is difficult to stay up-to-date given how fast the NLP field develops. However, this course provided enough background knowledge to learn those new topics on our own. All in all, very enjoyable learning experience and I am already applying some of the skills in my day job. Thanks so much!!

por Ivan S F

15 de mar. de 2020

The course is good. The course is worth taking. However, it is way too dense. There are very complicated concepts explained in too little time with too little context. I would suggest to break down the course into 3-4 courses within a specialization providing more examples, more context, more exercises to fully understand the material.

The final project is a nightmare where multiple different parts (amazon web services, tmux, docker, etc.) have to work all together. Not unexpectedly, a full range of errors, problems, and roadblocks arise when all these different parts have to work together for the project to work.

I finished the course including the final project and I am happy I took this course. However, the final project should have been better thought out before releasing it.

Thank you Anna and all the teaching staff for the course.

por Lefteris L

22 de sep. de 2019

This course offers a really good intro to all of the state of the art techniques used in NLP. Its course is structured by heavy impact papers from the literature and the instructors do a really good job in explaining.

The quizzes are good and help you understand the material.

If there is one thing I didn't like in this course, it was the programming assignments. Their structure was really big and aimed really long. Thus, I often felt that I didn't know what I was doing and for what reason. The assignments from Andrew Ng's Deep Learning's Specialization "Sequence Models" course were far better and helped me gain much intuition on how to code real tasks.

por Зубачев Д С

2 de oct. de 2019

It was a good course. All in one breath. I would like to have more practical tasks in which you need to write more code yourself, and not just fill in the missing cells. Of course, I am very grateful to Anna and Andrey for their work. Separately, we would like to note the penultimate task-the final project. It is complex and interesting. I believe that it would be correct to use the computing power of Azure instead of AWS.

por Arnaud R

15 de abr. de 2018

Great course !

Learned a lot. Removed one star because I felt they tried to jam too much content into 5weeks which resulted in some content to be rushed and given only a singular question in a quiz. The course would have deserved 1 or 2 more weeks to dilute the content a bit.

However you ll still learn very relevant skills in the assignements and the course provide a lot of links for you to learn more in X or Y subject.

por Neel K

17 de sep. de 2019

Course is well organized. Just some problems are related to assignments, There no exact guided steps for assignments and quiz. Lectures are more concerend about theory and less about pragmatic problems. Please make discussion forums active and more connected. Course does not have option to send message to anyone personally take help and advice which is something unrealistic.

por Joana N R

26 de ago. de 2020

Very complete course. Wish the instructors would provide more support and answer our questions in the discussion forums. The exercises seemed a bit complex in comparison to the lessons. Overall, great theoretical course. Loved the lessons, the practical quizzes and programming exercise not so much. Definitely recommend if you want to get familiar with NLP techniques.

por Игнатовская В А

6 de dic. de 2018

There were basic introduction as for me, without almost any proofs and mathematical constructions. It was interesting but after this course actually I can't say that now I can do it from the beginning to end for myself, only some functions to include in existing code. Last instruction about AWS was terrible! There were too many questions about it!!!!

por Fernaldy A F

29 de ago. de 2018

Great course but not easy one.. You must have required knowledge..

You need extra effort to finish quizzes or assignments, and also search in forum discussion or internet..

I think, the lectures are too theoretical, but that's good if you are curious or researchers that need to know about state of the art related NLP..

Overall this is worthy to take..

por Vivek G

25 de ago. de 2020

The course seems tough when you think just to learn from the slides, but in actual you need to learn a lot from the papers published for that topic. Overall the course was tough if you directly come to this 6th course of Machine Learning specialisation. The course tutor were very good, and explained with the best possible examples.

por Mark Z

11 de jun. de 2019

Overall great intro to NLP. Basic techniques like word embeddings and attention are explained quite well. However, some topics are not really easy to remember from this course, such as Topic modeling using LDA (which I understood much deeper during Bayesian Methods for Machine Learning course from the same specialization).

por João B P M J

8 de dic. de 2019

I think the provided material needs to be updated. Specially the material concerning TensorFlow. Many subjects and assignments let us wondering too much because it because there is a mismatch between the theoretical and the practical, and because the TensorFlow isn't updated it was hard to find additional help online.

por Zhaoqing X

24 de jul. de 2018

It's a very nice course! It involves so many aspects in NLP, and the assignments are especially valuable. The only thing I'm not satisfied is that it lacks enough help from the material and the forum when I got a bug from my assignments or confused by the instruction.

por Akash S

22 de may. de 2018

Very good course!! A big thanks to all the instructors. However I feel the course covered a lot of stuff which affected its focus. May be it would have been better to focus on fewer techniques but in greater detail both in theory and assignments.

por Helmut G

10 de jul. de 2018

Nice course. However, trying to pass the assignments can sometimes feel like a nightmare, because there is no feedback from the grader that would lead you into the right direction. Luckily you can get useful information in the discussion forum.

por Mika R

19 de nov. de 2019

I would recommend the mention of the library version in each given code to avoid the wrong use of the arguments and even attributes. For instance tf 2.0 do not have contrib and yet in certain part of the code, we are "required" to use that.

por PLN R

24 de dic. de 2018

Anna and group is great at teaching. However, a lot of graded assignments were a lot ambiguous with many important details missing. It would be a lot more helpful, if the content needed for assignment is explicitly mentioned! Thank you!

por Ajeet s

19 de abr. de 2019

The course is very nice. I wish there were some more examples in slides to understand the working of algorithms. Maybe its advance that's why I felt it.

If notes of every week were available then it would have been very beneficial.