GithubHelp home page GithubHelp logo

mannefedov / compling_nlp_hse_course Goto Github PK

View Code? Open in Web Editor NEW
171.0 8.0 75.0 250.13 MB

Материалы курса по компьютерной лингвистике Школы Лингвистики НИУ ВШЭ

Jupyter Notebook 98.73% HTML 1.27%
nlp computational-linguistics python machine-learning hse course natural-language-processing

compling_nlp_hse_course's Introduction

Материалы курса по компьютерной лингвистике (Natural Language Processing course materials)

Jupyter-ноутбуки курса

Вводная часть (1 модуль)

Основная часть

  1. Предобработка текста (Text preprocessing)
    Токенизация, лемматизация, стемминг, pymorphy, mystem, regex, razdel.
  2. Классификация текста (мешок слов) (Bag-of-words classification)
    TFIDF, CountVectorizer, LogReg, KNN, DecisionTrees, Naive Bayes, RandomForest, косинусная близость, тональность текста
  3. Поиск и исправление опечаток (Spellchecking)
    Алгоритм Норвига, расстояние Левенштейна, символьные нграммы, SymSpell.
  4. Базовое языковое моделирование (Basic Language Modelling)
    Вероятность слова, Ngram language model, перплексия, генерация текста.
  5. Тематическое моделирование (Topic modelling)
    Матричные разложения (SVD, NMF), LDA, перплексия, когерентность.
  6. Векторные представления слов (word2vec/fastext) (Word embeddings)
    cbow, skip-gram, negative sampling
  7. Convolutional Neural Networks for text classification
    CNN.
  8. RNN и извлечение именованных сущностей (Named Entity Recognition)
    LSTM, GRU, Bidirectional RNN, IOB кодировка, sequence labelling.
  9. Трансформеры. BERT и GPT (Transformers. BERT and GPT) (BERT, GPT)
    Transformer, BERT, HuggingFace, fine-tuning, text generation, sampling parameters (temperature, top_p, top_k)
  10. Трансформеры. Seq2Seq. Машинный перевод (Transformers. Seq2Seq. Machine Translation) multi-head attention, encoder-decoder model, bleu score
  11. Трансформеры. Дообучение на инструкциях (Transformers. Instruct fine-tuning)
    alpaca, dolly, flan-t5
  12. Трансформеры. PEFT
    quantization, LoRA, QLoRA
  13. Multimodality (text and images)
    CLIP, BLIP, Idefics, Stable diffusion
  14. Трансформеры. RLHF, DPO
    human feedback, DPO + QLoRA

Архивные jupyter-ноутбуки

Jupyter-notebooks in English

compling_nlp_hse_course's People

Contributors

danilsko avatar lapythie avatar mannefedov avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

compling_nlp_hse_course's Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.