# yandexdataschool/nlp_course

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/yandexdataschool-nlp-course).**

10,591 stars · 2,751 forks · Jupyter Notebook · MIT

## Links

- GitHub: https://github.com/yandexdataschool/nlp_course
- Homepage: https://lena-voita.github.io/nlp_course.html
- awesome-repositories: https://awesome-repositories.com/repository/yandexdataschool-nlp-course.md

## Description

YSDA course in Natural Language Processing

## Tags

### Artificial Intelligence & ML

- [Natural Language Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing.md) — Provides a comprehensive educational curriculum covering NLP from word embeddings to dialogue systems.
- [Homework Assignments](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-training/nlp-specific/homework-assignments.md) — Provides graded homework assignments that apply NLP techniques to real-world problems. ([source](https://lena-voita.github.io/))
- [Educational Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/generative-language-models/educational-implementations.md) — Provides hands-on assignments for building and visualizing n-gram and neural language models. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Dialogue Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-systems/dialogue-systems.md) — Teaches construction of task-oriented and open-domain conversational agents using retrieval and generative approaches.
- [Curricula](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-systems/dialogue-systems/curricula.md) — Teaches natural language processing through a structured course covering foundational embeddings through modern dialogue systems. ([source](https://lena-voita.github.io/))
- [Educational Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/model-fine-tuning-adaptation/language-model-training/educational-implementations.md) — Provides assignments for training n-gram and neural language models from scratch.
- [Sequence-to-Sequence Translation Tasks](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/speech-processing/sequence-to-sequence-tasks/sequence-to-sequence-translation-tasks.md) — Teaches building encoder-decoder models with attention mechanisms for translating text between languages.
- [Seq2Seq Attention Models](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-head-attention-mechanisms/additive-attention/seq2seq-attention-models.md) — Implements encoder-decoder architectures with attention mechanisms for sequence translation. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Conversational Dialogue Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-interfaces/conversational-dialogue-systems.md) — Constructs task-oriented and open-domain conversational agents using retrieval and generative approaches.
- [Word Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing/word-embeddings.md) — Teaches distributional semantics and vector representations using LSA, Word2Vec, and GloVe.
- [Neural Machine Translation](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-machine-translation.md) — Implements encoder-decoder models with attention mechanisms for machine translation tasks. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Part-of-Speech Taggers](https://awesome-repositories.com/f/artificial-intelligence-ml/part-of-speech-taggers.md) — Teaches part-of-speech tagging using structured perceptron and dynamic oracles. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Text Classification](https://awesome-repositories.com/f/artificial-intelligence-ml/text-classification.md) — Applies convolutional and recurrent networks to categorize text for sentiment or topic prediction.
- [Text Classifiers](https://awesome-repositories.com/f/artificial-intelligence-ml/text-classifiers.md) — Applies convolutional and recurrent neural networks to categorize text. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Word Alignment Extractions](https://awesome-repositories.com/f/artificial-intelligence-ml/word-alignment-extractions.md) — Learns word alignments between parallel texts using expectation-maximization algorithms. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Document Summarization](https://awesome-repositories.com/f/artificial-intelligence-ml/document-summarization.md) — Produces concise summaries of longer texts using extractive or abstractive methods. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Word Alignment](https://awesome-repositories.com/f/artificial-intelligence-ml/expectation-maximization/word-alignment.md) — Learns word alignments between parallel corpora using EM algorithms for translation tasks.
- [Educational Explanations](https://awesome-repositories.com/f/artificial-intelligence-ml/internal-state-analysis/educational-explanations.md) — Includes dedicated analysis sections in lectures to explain model internals. ([source](https://lena-voita.github.io/nlp_course.html))

### Education & Learning Resources

- [Natural Language Processing Resources](https://awesome-repositories.com/f/education-learning-resources/natural-language-processing-resources.md) — Teaches NLP concepts from word embeddings to dialogue systems through structured assignments and lectures.
- [Weekly Module Progressions](https://awesome-repositories.com/f/education-learning-resources/curriculum-structures/weekly-module-progressions.md) — Builds knowledge progressively through weekly modules from embeddings to dialogue systems.
- [Jupyter Notebook Curricula](https://awesome-repositories.com/f/education-learning-resources/jupyter-notebook-curricula.md) — Delivers interactive code cells and visualizations in the browser for experimenting with NLP models.
- [Lecture-Notebook Pairs](https://awesome-repositories.com/f/education-learning-resources/jupyter-notebook-curricula/lecture-notebook-pairs.md) — Pairs each lecture topic with a Jupyter notebook for immediate hands-on practice.
- [Blog-Style Lectures](https://awesome-repositories.com/f/education-learning-resources/machine-learning-lectures/blog-style-lectures.md) — Delivers lecture content as intuitive, engaging blog-style pages that are complete and up-to-date. ([source](https://lena-voita.github.io/nlp_course.html))
- [NLP Lecture Slides](https://awesome-repositories.com/f/education-learning-resources/machine-learning-lectures/nlp-lecture-slides.md) — Provides structured lecture slides covering core natural language processing topics. ([source](https://lena-voita.github.io/))
- [Programming Assignments](https://awesome-repositories.com/f/education-learning-resources/programming-assignments.md) — Provides weekly programming assignments that implement core NLP algorithms from scratch.
- [NLP Seminar Exercises](https://awesome-repositories.com/f/education-learning-resources/practical-assignments/nlp-seminar-exercises.md) — Offers seminar materials with hands-on exercises to reinforce NLP concepts taught in lectures. ([source](https://lena-voita.github.io/))
- [Paper Summaries](https://awesome-repositories.com/f/education-learning-resources/research-papers/paper-summaries.md) — Summarizes key results and reasoning from top NLP papers for quick understanding.
- [Summaries](https://awesome-repositories.com/f/education-learning-resources/research-papers/summaries.md) — Summarizes key results and reasoning from influential NLP papers. ([source](https://lena-voita.github.io/nlp_course.html))
- [Research Skill Development](https://awesome-repositories.com/f/education-learning-resources/research-skill-development.md) — Guides learners to identify flaws, hypothesize improvements, and explore prior work. ([source](https://lena-voita.github.io/nlp_course.html))

### Part of an Awesome List

- [Dialogue Systems](https://awesome-repositories.com/f/awesome-lists/ai/dialogue-systems.md) — Constructs task-oriented and open-domain conversational agents using retrieval and generative approaches. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Python Data Science Courses](https://awesome-repositories.com/f/awesome-lists/learning/machine-learning-courses/python-data-science-courses.md) — Teaches NLP using Python with NumPy, PyTorch, and NLTK for all assignments and examples.
- [Programming Assignments](https://awesome-repositories.com/f/awesome-lists/learning/nlp-learning-resources/programming-assignments.md) — Provides weekly programming assignments that implement core NLP algorithms from scratch.
- [Text Summarization](https://awesome-repositories.com/f/awesome-lists/ai/text-summarization.md) — Produces concise summaries by selecting key sentences or generating new text from source documents. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
- [Python NLP Libraries](https://awesome-repositories.com/f/awesome-lists/devtools/python-nlp-libraries.md) — Teaches NLP algorithms using Python with NumPy, PyTorch, and NLTK for all assignments and examples.
- [Educational Curricula](https://awesome-repositories.com/f/awesome-lists/devtools/python-nlp-libraries/educational-curricula.md) — Teaches NLP algorithms using Python with NumPy, PyTorch, and NLTK for all assignments and examples.

### Business & Productivity Software

- [Scaffolded Implementations](https://awesome-repositories.com/f/business-productivity-software/task-workflow-automation/productivity-task-management/task-management/tasks-frameworks/agent-task-assignment/student-assignments/scaffolded-implementations.md) — Guides students through implementing complex algorithms with pre-written stubs and tests.

### Software Engineering & Architecture

- [Algorithm Scaffolding](https://awesome-repositories.com/f/software-engineering-architecture/scaffolding-generators/content-scaffolding/algorithm-scaffolding.md) — Provides pre-written stubs and tests for implementing attention mechanisms and structured perceptrons.

### Data & Databases

- [Domain Adaptation Techniques](https://awesome-repositories.com/f/data-databases/object-relational-mappers/domain-models/domain-adaptation-techniques.md) — Adapts a general machine translation model to a specific domain by matching features and distilling knowledge. ([source](https://cdn.jsdelivr.net/gh/yandexdataschool/nlp_course@2025/README.md))
