このコースについて
148,668 最近の表示

次における1の1コース

100%オンライン

自分のスケジュールですぐに学習を始めてください。

柔軟性のある期限

スケジュールに従って期限をリセットします。

上級レベル

約33時間で修了

推奨:5 weeks of study, 4-5 hours per week...

英語

字幕:英語

習得するスキル

ChatterbotTensorflowDeep LearningNatural Language Processing

次における1の1コース

100%オンライン

自分のスケジュールですぐに学習を始めてください。

柔軟性のある期限

スケジュールに従って期限をリセットします。

上級レベル

約33時間で修了

推奨:5 weeks of study, 4-5 hours per week...

英語

字幕:英語

シラバス - 本コースの学習内容

1
5時間で修了

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).

...
11件のビデオ (合計114分), 3 readings, 3 quizzes
11件のビデオ
Welcome video5 分
Main approaches in NLP7 分
Brief overview of the next weeks7 分
[Optional] Linguistic knowledge in NLP10 分
Text preprocessing14 分
Feature extraction from text14 分
Linear models for sentiment analysis10 分
Hashing trick in spam filtering17 分
Neural networks for words14 分
Neural networks for characters8 分
3件の学習用教材
Prerequisites check-list2 分
Hardware for the course5 分
Getting started with practical assignments20 分
2の練習問題
Classical text mining10 分
Simple neural networks for text10 分
2
5時間で修了

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.

...
8件のビデオ (合計84分), 2 readings, 3 quizzes
8件のビデオ
Perplexity: is our model surprised with a real text?8 分
Smoothing: what if we see new n-grams?7 分
Hidden Markov Models13 分
Viterbi algorithm: what are the most probable tags?11 分
MEMMs, CRFs and other sequential models for Named Entity Recognition11 分
Neural Language Models9 分
Whether you need to predict a next word or a label - LSTM is here to help!11 分
2件の学習用教材
Perplexity computation10 分
Probabilities of tag sequences in HMMs20 分
2の練習問題
Language modeling15 分
Sequence tagging with probabilistic models20 分
3
5時間で修了

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.

...
8件のビデオ (合計83分), 3 quizzes
8件のビデオ
Explicit and implicit matrix factorization13 分
Word2vec and doc2vec (and how to evaluate them)10 分
Word analogies without magic: king – man + woman != queen11 分
Why words? From character to sentence embeddings11 分
Topic modeling: a way to navigate through text collections7 分
How to train PLSA?6 分
The zoo of topic models13 分
2の練習問題
Word and sentence embeddings15 分
Topic Models10 分
4
5時間で修了

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.

...
9件のビデオ (合計98分), 4 quizzes
9件のビデオ
Noisy channel: said in English, received in French6 分
Word Alignment Models12 分
Encoder-decoder architecture6 分
Attention mechanism9 分
How to deal with a vocabulary?12 分
How to implement a conversational chat-bot?11 分
Sequence to sequence learning: one-size fits all?10 分
Get to the point! Summarization with pointer-generator networks12 分
3の練習問題
Introduction to machine translation10 分
Encoder-decoder architectures20 分
Summarization and simplification15 分
4.6
94件のレビューChevron Right

29%

コース終了後に新しいキャリアをスタートした

30%

コースが具体的なキャリアアップにつながった

33%

昇給や昇進につながった

自然言語処理 からの人気レビュー

by 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!

by MVMar 18th 2019

Definitely best course in the Specialization! Lecturers, projects and forum - everything is super organized. Only StarSpace was pain in the ass, but I managed :)

講師

Avatar

Anna Potapenko

Researcher
HSE Faculty of Computer Science
Avatar

Alexey Zobnin

Accosiate professor
HSE Faculty of Computer Science
Avatar

Anna Kozlova

Team Lead
Yandex
Avatar

Sergey Yudin

Analyst-developer
Yandex
Avatar

Andrei Zimovnov

Senior Lecturer
HSE Faculty of Computer Science

ロシア国立研究大学経済高等学院(National Research University Higher School of Economics)について

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. Learn more on www.hse.ru...

Advanced Machine Learningの専門講座について

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

よくある質問

  • 修了証に登録すると、すべてのビデオ、テスト、およびプログラミング課題(該当する場合)にアクセスできます。ピアレビュー課題は、セッションが開始してからのみ、提出およびレビューできます。購入せずにコースを検討することを選択する場合、特定の課題にアクセスすることはできません。

  • コースに登録する際、専門講座のすべてのコースにアクセスできます。コースの完了時には修了証を取得できます。電子修了証が成果のページに追加され、そこから修了証を印刷したり、LinkedInのプロフィールに追加したりできます。コースの内容の閲覧のみを希望する場合は、無料でコースを聴講できます。

さらに質問がある場合は、受講者向けヘルプセンターにアクセスしてください。