ai-forever / sage
SAGE: Spelling correction, corruption and evaluation for multiple languages
☆131Updated last month
Related projects ⓘ
Alternatives and complementary repositories for sage
- Augmentex — a library for augmenting texts with errors☆52Updated 4 months ago
- The tiniest sentence encoder for Russian language☆189Updated 3 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆58Updated last month
- Russian Corpus of Linguistic Acceptability☆41Updated last month
- ☆58Updated 9 months ago
- Библиотека для извлечения статистик из текстов на русском языке.☆103Updated last year
- "Руформеры" - список популярных базовых моделей на основе трансформеров для решения задач по автоматической обработке русского языка☆36Updated last year
- RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.☆93Updated last year
- Проект для перевода чисел, записанных в текстовом виде на русском языке.☆100Updated 3 years ago
- Compact high quality word embeddings for Russian language☆185Updated last year
- Deep Learning for Speech☆80Updated last week
- A Python wrapper for the RuWordNet thesaurus☆57Updated 4 months ago
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆57Updated last year
- Russian SuperGLUE benchmark☆108Updated last year
- Deep Learning based NLP modeling for Russian language☆224Updated last year
- Rule-based token, sentence segmentation for Russian language☆249Updated last year
- Fine-tuned Multilingual BERT and Multilingual USE for sentiment analysis in Russian. RuReviews, RuSentiment, Kaggle Russian News Dataset,…☆50Updated 3 years ago
- Materials of transformers lecture course☆73Updated 3 months ago
- Links to Russian corpora + Python functions for loading and parsing☆281Updated last year
- ☆78Updated last year
- Russian/English/Estonian/Finnish/Swedish phonetic algorithm based on Soundex and Metaphone☆46Updated 2 years ago
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆46Updated 2 months ago
- Pipeline for easy fine-tuning of BERT architecture for sequence classification☆22Updated last year
- Question answering on russian with XLMRobertaLarge as a service☆21Updated 3 years ago
- BSNLP 2021☆32Updated 2 weeks ago
- Материалы курса по компьютерной лингвистике Школы Лингвистики НИУ ВШЭ☆179Updated this week
- A new second practical assignment for Huawei's NLP course☆16Updated 8 months ago
- Gazeta: Dataset for automatic summarization of Russian news / Газета: набор данных для автоматического реферирования на русском языке☆32Updated 3 years ago