vifirsanova

nlp-huawei-project. A closed domain model for question-answering in Russian built with transfer learning techniques. The model is fine-tuned on a custom dataset collected with the methodology described in the SQuAD original paper.

hse-python-course. Авторский курс Виктории Фирсановой по Python для Data Science и NLP. Разработан специально для петербургского кампуса НИУ ВШЭ

ASD-QA. Jupyter Notebook

stat-llm. Syllable-based tokenization NLP model

empi. Empathic Machine Processors for Inclusion (EMPI)

AGGILE. automated graph generation 4 inference & language exploration

llm-tutorial. Туториал по работе с большими языковыми моделями

asr-multiagent. Multiagent system for accessible Automated Speech Recognition (ASR) and function calling in smart home ecosystem

text-to-image-explainable. Supplementary material for the paper "What Do Text-to-Image Models Know about the Languages of the World?" by Victoria Firsanova

100-days-of-code. Jupyter Notebook

NLP-Discussion-Group. Jupyter Notebook

nlp-course. Jupyter Notebook