课程信息
4.7
186 个评分
44 个审阅
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. 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 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....
Stacks
Globe

100% 在线课程

立即开始,按照自己的计划学习。
Calendar

可灵活调整截止日期

根据您的日程表重置截止日期。
Advanced Level

高级

Clock

Approx. 30 hours to complete

建议:5 weeks of study, 4-5 hours per week...
Comment Dots

English

字幕:English...

您将获得的技能

ChatterbotTensorflowDeep LearningNatural Language Processing
Stacks
Globe

100% 在线课程

立即开始,按照自己的计划学习。
Calendar

可灵活调整截止日期

根据您的日程表重置截止日期。
Advanced Level

高级

Clock

Approx. 30 hours to complete

建议:5 weeks of study, 4-5 hours per week...
Comment Dots

English

字幕:English...

教学大纲 - 您将从这门课程中学到什么

Week
1
Clock
完成时间为 5 小时

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)....
Reading
11 个视频(共 114 分钟), 3 个阅读材料, 3 个测验
Video11 个视频
Welcome video5分钟
Main approaches in NLP7分钟
Brief overview of the next weeks7分钟
[Optional] Linguistic knowledge in NLP10分钟
Text preprocessing14分钟
Feature extraction from text14分钟
Linear models for sentiment analysis10分钟
Hashing trick in spam filtering17分钟
Neural networks for words14分钟
Neural networks for characters8分钟
Reading3 个阅读材料
Prerequisites check-list2分钟
Hardware for the course5分钟
Getting started with practical assignments20分钟
Quiz2 个练习
Classical text mining10分钟
Simple neural networks for text10分钟
Week
2
Clock
完成时间为 5 小时

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....
Reading
8 个视频(共 84 分钟), 2 个阅读材料, 3 个测验
Video8 个视频
Perplexity: is our model surprised with a real text?8分钟
Smoothing: what if we see new n-grams?7分钟
Hidden Markov Models13分钟
Viterbi algorithm: what are the most probable tags?11分钟
MEMMs, CRFs and other sequential models for Named Entity Recognition11分钟
Neural Language Models9分钟
Whether you need to predict a next word or a label - LSTM is here to help!11分钟
Reading2 个阅读材料
Perplexity computation10分钟
Probabilities of tag sequences in HMMs20分钟
Quiz2 个练习
Language modeling15分钟
Sequence tagging with probabilistic models20分钟
Week
3
Clock
完成时间为 5 小时

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....
Reading
8 个视频(共 83 分钟), 3 个测验
Video8 个视频
Explicit and implicit matrix factorization13分钟
Word2vec and doc2vec (and how to evaluate them)10分钟
Word analogies without magic: king – man + woman != queen11分钟
Why words? From character to sentence embeddings11分钟
Topic modeling: a way to navigate through text collections7分钟
How to train PLSA?6分钟
The zoo of topic models13分钟
Quiz2 个练习
Word and sentence embeddings15分钟
Topic Models10分钟
Week
4
Clock
完成时间为 5 小时

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....
Reading
9 个视频(共 98 分钟), 4 个测验
Video9 个视频
Noisy channel: said in English, received in French6分钟
Word Alignment Models12分钟
Encoder-decoder architecture6分钟
Attention mechanism9分钟
How to deal with a vocabulary?12分钟
How to implement a conversational chat-bot?11分钟
Sequence to sequence learning: one-size fits all?10分钟
Get to the point! Summarization with pointer-generator networks12分钟
Quiz3 个练习
Introduction to machine translation10分钟
Encoder-decoder architectures20分钟
Summarization and simplification15分钟
4.7

热门审阅

创建者 GYMar 24th 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!

创建者 TLJul 8th 2018

Anna is a great instructor. She can explain the concept and mathematical formulas in a clear way. The design of assignment is both interesting and practical.

讲师

Anna Potapenko

Researcher
HSE Faculty of Computer Science

Alexey Zobnin

Accosiate professor
HSE Faculty of Computer Science

Anna Kozlova

Team Lead
Yandex

Sergey Yudin

Analyst-developer
Yandex

Andrei Zimovnov

Senior Lecturer
HSE Faculty of Computer Science

关于 National Research University Higher School of Economics

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 communications, IT, mathematics, engineering, and more. Learn more on www.hse.ru...

关于 Advanced Machine Learning 专项课程

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....
Advanced Machine Learning

常见问题

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

还有其他问题吗?请访问 学生帮助中心