This 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.
提供方
高级机器学习 專項課程国立高等经济大学課程信息
136,535 次近期查看
學生職業成果
38%
完成這些課程後已開始新的職業生涯
42%
通過此課程獲得實實在在的工作福利
43%
加薪或升職
可分享的證書
完成後獲得證書
100% 在線
立即開始，按照自己的計劃學習。
第 6 門課程（共 7 門）
可靈活調整截止日期
根據您的日程表重置截止日期。
高級
完成時間大約為32 小時
英語（English）
字幕：英語（English）, 韓語
您將獲得的技能
ChatterbotTensorflowDeep LearningNatural Language Processing
學生職業成果
38%
完成這些課程後已開始新的職業生涯
42%
通過此課程獲得實實在在的工作福利
43%
加薪或升職
可分享的證書
完成後獲得證書
100% 在線
立即開始，按照自己的計劃學習。
第 6 門課程（共 7 門）
可靈活調整截止日期
根據您的日程表重置截止日期。
高級
完成時間大約為32 小時
英語（English）
字幕：英語（English）, 韓語
提供方
国立高等经济大学
National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communicamathematics, engineering, and more.
教學大綱 - 您將從這門課程中學到什麼
完成時間為 5 小時
Intro and text classification
In this module we will have two parts: first, a broad overview of NLP area and our course goals, and second, a text classification task. It is probably the most popular task that you would deal with in real life. It could be news flows classification, sentiment analysis, spam filtering, etc. You will learn how to go from raw texts to predicted classes both with traditional methods (e.g. linear classifiers) and deep learning techniques (e.g. Convolutional Neural Nets).
完成時間為 5 小時
12 個視頻 （總計 115 分鐘）, 4 個閱讀材料, 3 個測驗
12 個視頻
About this course2分鐘
Welcome video5分鐘
Main approaches in NLP7分鐘
Brief overview of the next weeks7分鐘
[Optional] Linguistic knowledge in NLP10分鐘
Text preprocessing14分鐘
Feature extraction from text14分鐘
Linear models for sentiment analysis10分鐘
Hashing trick in spam filtering17分鐘
Neural networks for words14分鐘
Neural networks for characters8分鐘
4 個閱讀材料
About the University10分鐘
Prerequisites check-list2分鐘
Hardware for the course5分鐘
Getting started with practical assignments20分鐘
2 個練習
Classical text mining10分鐘
Simple neural networks for text10分鐘
完成時間為 5 小時
Language modeling and sequence tagging
In this module we will treat texts as sequences of words. You will learn how to predict next words given some previous words. This task is called language modeling and it is used for suggests in search, machine translation, chat-bots, etc. Also you will learn how to predict a sequence of tags for a sequence of words. It could be used to determine part-of-speech tags, named entities or any other tags, e.g. ORIG and DEST in "flights from Moscow to Zurich" query. We will cover methods based on probabilistic graphical models and deep learning.
完成時間為 5 小時
8 個視頻 （總計 84 分鐘）, 2 個閱讀材料, 3 個測驗
8 個視頻
Perplexity: is our model surprised with a real text?8分鐘
Smoothing: what if we see new n-grams?7分鐘
Hidden Markov Models13分鐘
Viterbi algorithm: what are the most probable tags?11分鐘
MEMMs, CRFs and other sequential models for Named Entity Recognition11分鐘
Neural Language Models9分鐘
Whether you need to predict a next word or a label - LSTM is here to help!11分鐘
2 個閱讀材料
Perplexity computation10分鐘
Probabilities of tag sequences in HMMs20分鐘
2 個練習
Language modeling15分鐘
Sequence tagging with probabilistic models20分鐘
完成時間為 5 小時
Vector Space Models of Semantics
This module is devoted to a higher abstraction for texts: we will learn vectors that represent meanings. First, we will discuss traditional models of distributional semantics. They are based on a very intuitive idea: "you shall know the word by the company it keeps". Second, we will cover modern tools for word and sentence embeddings, such as word2vec, FastText, StarSpace, etc. Finally, we will discuss how to embed the whole documents with topic models and how these models can be used for search and data exploration.
完成時間為 5 小時
8 個視頻 （總計 83 分鐘）
8 個視頻
Explicit and implicit matrix factorization13分鐘
Word2vec and doc2vec (and how to evaluate them)10分鐘
Word analogies without magic: king – man + woman != queen11分鐘
Why words? From character to sentence embeddings11分鐘
Topic modeling: a way to navigate through text collections7分鐘
How to train PLSA?6分鐘
The zoo of topic models13分鐘
2 個練習
Word and sentence embeddings15分鐘
Topic Models10分鐘
完成時間為 5 小時
Sequence to sequence tasks
Nearly any task in NLP can be formulates as a sequence to sequence task: machine translation, summarization, question answering, and many more. In this module we will learn a general encoder-decoder-attention architecture that can be used to solve them. We will cover machine translation in more details and you will see how attention technique resembles word alignment task in traditional pipeline.
完成時間為 5 小時
9 個視頻 （總計 98 分鐘）
9 個視頻
Noisy channel: said in English, received in French6分鐘
Word Alignment Models12分鐘
Encoder-decoder architecture6分鐘
Attention mechanism9分鐘
How to deal with a vocabulary?12分鐘
How to implement a conversational chat-bot?11分鐘
Sequence to sequence learning: one-size fits all?10分鐘
Get to the point! Summarization with pointer-generator networks12分鐘
3 個練習
Introduction to machine translation10分鐘
Encoder-decoder architectures20分鐘
Summarization and simplification15分鐘
審閱
來自自然语言处理的熱門評論
由 YY 提供2019年1月1日
I like this course very much. It is a good introduction for NLP. But if you want to know more about the NLP, you need to search and read a lot of posts during the learning process.
由 AS 提供2020年5月18日
The course had an advanced content and was taught at a good pace. Though there are some concepts which were not elaborated and needed to be understood from different sources.
由 AJ 提供2020年4月23日
This is basic to advanced level course. you should have significant amount of knowledge in the field, if not you have to do additional research .Over all good course.
由 DW 提供2020年8月2日
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.
關於 高级机器学习 專項課程
This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings.
常見問題
我什么时候能够访问课程视频和作业？
讲座和作业的访问权限取决于您的注册类型。如果您以旁听模式参加课程，则可以免费查看大多数课程资料。要访问评分作业并获得证书，您需要在旁听期间或之后购买证书体验。如果看不到旁听选项：
- 课程可能不提供旁听选项。您可以尝试免费试用，也可以申请助学金。
- 课程可能会改为提供'完整课程，没有证书'。通过此选项，您可以查看所有课程材料、提交所要求的作业，以及获得最终成绩。这也意味着您将无法购买证书体验。
我订阅此专项课程后会得到什么？
您注册课程后，将有权访问专项课程中的所有课程，并且会在完成课程后获得证书。您的电子课程证书将添加到您的成就页中，您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容，可以免费旁听课程。
Is financial aid available?
是的，Coursera 可以为无法承担费用的学生提供助学金。通过点击左侧“注册”按钮下的“助学金”链接可以申请助学金。您可以根据屏幕提示完成申请，申请获批后会收到通知。您需要针对专项课程中的每一门课程完成上述步骤，包括毕业项目。了解更多。
完成课程后，我会获得大学学分吗？
此课程不提供大学学分，但部分大学可能会选择接受课程证书作为学分。查看您的合作院校，了解详情。Coursera 上的在线学位和 Mastertrack™ 证书提供获得大学学分的机会。
還有其他問題嗎？請訪問 學生幫助中心。
