-
Novosibirsk State University
- Novosibirsk, Russia
- https://scholar.google.ru/citations?user=3AJKH38AAAAJ
- https://orcid.org/0000-0002-0457-0698
- https://t.me/Bond_005
-
ru_llm_instruct Public
Experiments to build an instruct large language model for Russian language.
-
checker Public
This is a complexity checker of samples in SFT datasets for LLM
Apache License 2.0 UpdatedOct 3, 2024 -
pisets Public
The python library and service for automatic speech recognition and transcribing in Russian and English
-
irm_experiments Public
This repository is devoted to my experiments with invariant risk minimization (IRM) for deep learning
Jupyter Notebook Apache License 2.0 UpdatedAug 4, 2024 -
-
self-adaptive-hierarchy Public
Experiments with self-adaptive hierarchical learning for text classification
Apache License 2.0 UpdatedMar 9, 2024 -
nsu-ai Public
This repository devoted to a multimodal AI system for the AIJ contest "Strong AI"
-
runne_contrastive_ner Public
This project is concerned with my participating in the RuNNE competition https://github.com/dialogue-evaluation/RuNNE
-
wav2vec2-gpt-mt Public
Wav2Vec2-mGPT speech encoder-decoder with multitask learning
-
deep_ner Public
Named entity recognizer based on ELMo or BERT as feature extractor and CRF as final classifier
-
impartial_text_cls Public
Text classifier, based on the BERT and a Bayesian neural network, which can train on small labeled texts and doubt its decision.
-
-
sequence_classifier Public
Sequence classifier based on SRU (cf. https://arxiv.org/abs/1709.02755).
-
constt Public
Constrastive learning for Wav2Vec2-based speech-to-text
Apache License 2.0 UpdatedOct 24, 2022 -
neuro_tagger Public
Text tagger based on recurrent neural network. It can be used as NER, dependency parser, morphoanalyzer etc.
-
tabular_deep_learning Public
My experiments with deep neural networks for tabular data processing
Jupyter Notebook Apache License 2.0 UpdatedJun 3, 2022 -
snn Public
Tabular data processing based on self-normalizing neural networks
Apache License 2.0 UpdatedFeb 28, 2022 -
yandex-shifts-weather Public
The best solution of the Weather Prediction track in the Yandex Shifts challenge
-
seq2seq Public
LSTM-Seq2Seq on the bases of Keras with the simple ScikitLearn interface
-
This repository is devoted to my Natural Language Processing course in the Novosibirsk State University
-
speech_commands Public
Recognizer of speech commands and other sounds based on pre-trained MobileNet
-
factRuEval-2016 Public
Forked from dialogue-evaluation/factRuEval-2016http://www.dialog-21.ru/evaluation/2016/letter/
-
bert_ner Public
Named entity recognizer based on BERT and CRF
-
speech_cleaner Public
Speech cleaner from complex noises based on SEDNN https://github.com/yongxuUSTC/sednn
Apache License 2.0 UpdatedJul 3, 2018 -
rnnmorph Public
Forked from IlyaGusev/rnnmorphМорфологический анализатор на основе нейронных сетей и pymorphy2
-
soroka Public
Узнай, хорошо или плохо говорят о тебе или твоей фирме в Интернете! Наша "Сорока" с искусственным интеллектом принесёт тебе это на своём хвосте
Apache License 2.0 UpdatedMay 19, 2018 -
KenLM: Faster and Smaller Language Model Queries
C++ Other UpdatedMay 11, 2018 -
asr_cdp Public
Automatic voice commands recognition by the Vintsyuk algorithm based on dynamic programming and piecewise-constant model of speech signal.
C BSD 2-Clause "Simplified" License UpdatedJan 10, 2018 -
-
conll2000_crf Public
CRF Chunker for CoNLL2000 task
Python GNU General Public License v3.0 UpdatedApr 15, 2017