Hello, my name is Pavel Egizaryan, I am a Ph.D. in Linguistics with 3 years of experience in IT (automation, data analysis, and rule-based NLP). Currently, I'm studying Machine Learning and trying to use it for tasks in my fields of interest.
- Currency rate — prediction of currency rates based on classical ML algorithms such as MLP Regressor and Random Forest Regressor.
- Avestan model — creating a model on a dataset of (almost?) all the texts in the Avestan language (in progress).
- Persian OCR — creating an OCR for the Persian cuneiform (in progress).
- Septuagint classifier — book classifier for the Ancient Greek translation of the Hebrew Bible that can be used for exploring textual connections between Septuagint and the Ancient Greek texts that were written later (in progress).
- Is it Pushkin? — classifier of the greatest Russian poet's authorship, used for exploring one of the mysteries of 19th-century Russian literature (in progress).
- Disaster tweets — classifier of tweets by the description of real and fake disasters (if any), made for the Kaggle competition.