About this Course
최근 조회 143,379

다음 전문 분야의 1개 강좌 중 1번째 강좌:

100% 온라인

지금 바로 시작해 나만의 일정에 따라 학습을 진행하세요.

유동적 마감일

일정에 따라 마감일을 재설정합니다.

고급 단계

완료하는 데 약 33시간 필요

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

영어

자막: 영어

귀하가 습득할 기술

ChatterbotTensorflowDeep LearningNatural Language Processing

다음 전문 분야의 1개 강좌 중 1번째 강좌:

100% 온라인

지금 바로 시작해 나만의 일정에 따라 학습을 진행하세요.

유동적 마감일

일정에 따라 마감일을 재설정합니다.

고급 단계

완료하는 데 약 33시간 필요

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

영어

자막: 영어

강의 계획 - 이 강좌에서 배울 내용

1
완료하는 데 5시간 필요

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 videos (Total 114 min), 3 readings, 3 quizzes
11개의 동영상
Welcome video5m
Main approaches in NLP7m
Brief overview of the next weeks7m
[Optional] Linguistic knowledge in NLP10m
Text preprocessing14m
Feature extraction from text14m
Linear models for sentiment analysis10m
Hashing trick in spam filtering17m
Neural networks for words14m
Neural networks for characters8m
3개의 읽기 자료
Prerequisites check-list2m
Hardware for the course5m
Getting started with practical assignments20m
2개 연습문제
Classical text mining10m
Simple neural networks for text10m
2
완료하는 데 5시간 필요

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 videos (Total 84 min), 2 readings, 3 quizzes
8개의 동영상
Perplexity: is our model surprised with a real text?8m
Smoothing: what if we see new n-grams?7m
Hidden Markov Models13m
Viterbi algorithm: what are the most probable tags?11m
MEMMs, CRFs and other sequential models for Named Entity Recognition11m
Neural Language Models9m
Whether you need to predict a next word or a label - LSTM is here to help!11m
2개의 읽기 자료
Perplexity computation10m
Probabilities of tag sequences in HMMs20m
2개 연습문제
Language modeling15m
Sequence tagging with probabilistic models20m
3
완료하는 데 5시간 필요

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 videos (Total 83 min), 3 quizzes
8개의 동영상
Explicit and implicit matrix factorization13m
Word2vec and doc2vec (and how to evaluate them)10m
Word analogies without magic: king – man + woman != queen11m
Why words? From character to sentence embeddings11m
Topic modeling: a way to navigate through text collections7m
How to train PLSA?6m
The zoo of topic models13m
2개 연습문제
Word and sentence embeddings15m
Topic Models10m
4
완료하는 데 5시간 필요

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 videos (Total 98 min), 4 quizzes
9개의 동영상
Noisy channel: said in English, received in French6m
Word Alignment Models12m
Encoder-decoder architecture6m
Attention mechanism9m
How to deal with a vocabulary?12m
How to implement a conversational chat-bot?11m
Sequence to sequence learning: one-size fits all?10m
Get to the point! Summarization with pointer-generator networks12m
3개 연습문제
Introduction to machine translation10m
Encoder-decoder architectures20m
Summarization and simplification15m
4.6
94개의 리뷰Chevron Right

38%

이 강좌를 수료한 후 새로운 경력 시작하기

36%

이 강좌를 통해 확실한 경력상 이점 얻기

33%

급여 인상 또는 승진하기

자연 언어 처리의 최상위 리뷰

대학: 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!

대학: 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 :)

강사

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

국립 연구 고등 경제 대학 정보

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...

고급 기계 학습 전문 분야 정보

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....
고급 기계 학습

자주 묻는 질문

  • 강좌에 등록하면 바로 모든 비디오, 테스트 및 프로그래밍 과제(해당하는 경우)에 접근할 수 있습니다. 상호 첨삭 과제는 이 세션이 시작된 경우에만 제출하고 검토할 수 있습니다. 강좌를 구매하지 않고 살펴보기만 하면 특정 과제에 접근하지 못할 수 있습니다.

  • 강좌를 등록하면 전문 분야의 모든 강좌에 접근할 수 있고 강좌를 완료하면 수료증을 취득할 수 있습니다. 전자 수료증이 성취도 페이지에 추가되며 해당 페이지에서 수료증을 인쇄하거나 LinkedIn 프로필에 수료증을 추가할 수 있습니다. 강좌 내용만 읽고 살펴보려면 해당 강좌를 무료로 청강할 수 있습니다.

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.