NLP_Datasets. My NLP datasets for Russian language
393chatbot. Русскоязычный генеративный чатбот с профилем и фактами
259GrammarEngine. Грамматический Словарь Русского Языка (+ английский, японский, etc)
78rulemma. Лемматизатор для русскоязычных текстов
46MNIST_Boosting. Comparison of XGBoost, LightGBM and CatBoost on MNIST classification problem
41verslibre. Using transformers to generate Russian poetry
36rusyllab. Simple Python package for breaking Russian words into syllables
32rupostagger. Part-of-Speech Tagger for Russian language
23rutokenizer. Russian text segmenter and tokenizer
18LM-finetune. Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa
14pushkin. Генеративные текстовые модели
14StressModel. Neural model for prediction of stress position in Russian words
13paraphraser. Поэтический перефразировщик
9RussianDictionary. Russian Lexicon and Syntax Rules
8MLBootCampV. http://mlbootcamp.ru/round/12/sandbox/
7WordRepresentations. Сравнение нескольких способов представления слов для построения языковых моделей
6Rifma. Dataset with annotation of Russian-language poems
5ruword2tags. Морфологический анализатор слов для русского языка
5CorpusSearch. Полнотекстовый поиск по текстовому корпусу с помощью Lucene.NET
5vector2text. Generate Russian text using GPT model given LaBSE text embedding vector
5RussianPoetryScansionTool. Detection of poetic meter, rhyme, and stress placement in the texts of Russian accentual-syllabic poems and songs.
5NGrams. Работа с n-граммами: сбор и использование для оценки текста
4transcriber. Model to convert text to phonetic transcription and vice versa
3LM-pretrain. Char-level language model pretraining code and scripts
3Word2Vec. Continuous word representation tools
3mamba. Python
2word2lemma. Эксперименты с лемматизацией
2word_embedders. Character-level autoencoder models for words
2Spellchecker. Rule- and dictionary-based spellchecker with emphasize on precision over recall
2rupostagger2. Простая нейросетевая модель для частеречной разметки
2sent_embedders. Experiments with sentence embedding models
1QuoraQuestionPairs. Deep learning models for Kaggle NLP competition 'Quora Question Pairs'
1math. Conversational data generator
1SentimentAnalysis. C# and Python tools and models for review sentiment analysis
1character-tokenizer. A character tokenizer for HuggingFace Transformers
1ruchunker. NP chunker for Russian language
1MorphoRuEval2017. Part-of-speech tagger and lemmatizer for MorphoRuEval2017
1arithmetic_robustness. Evaluating How Whitespace Distortions in Prompts Affect Large Language Models' Arithmetic Problem-Solving Accuracy
1ML-Challenge-3. Jupyter Notebook
1NLP_Comp. Solutions for NLP competitions
1word_is_noun. Binary classification of Russian wordforms using RNN/LSTM character language model
1MLBootCampIII. http://mlbootcamp.ru/championship/10/
1