CV

Education

• MSc in Speech and Language Processing, The University of Edinburgh, 2017-2018
  • Thesis: Grapheme-to-Metaphoneme Conversion for Unisyn and Combilex Baseform Transcriptions.
  • Relevant coursework: Speech Synthesis, Automatic Speech Recognition, Computer Programming for Speech and Language Processing, Introduction to Phonology and Phonetics, Accelerated Natural Language Processing.
• BA in Linguistics, Bashkir State University, 2013-2017

Work experience

• NLP Data Scientist, (Ufa, 2018 - present)
  • RN-BashNIPIneft, LLC (Research Institute of Rosneft)
  • Duties included:
    • Developing machine learning models for text classification and named entity recognition.
    • Adapted a pre-trained speech recognition system to an oil and gas domain.
    • Built a dialogue system for enterprise software.

Skills

• Python: data analysis, backend web development, OOP.
• Natural Language Processing: classical techniques (n-grams, tf-idf), deep learning approaches (RNNs, Seq2Seq, Transformers).
• Speech Processing: speech data analysis, feature extraction, concatenative and neural speech synthesis, automatic speech recognition.
• Machine Learning
• Linguistics: Phonetics, phonology of English, IPA, morphology.
• Languages: Russian (native), English (advanced), German (basic), Italian (Basic).

Scholarships and Awards

• First Prize at Data Science Championship. Moscow, november 2020
  • Best ML model to predict personality traits based on textual data.
• First Prize at AC-VO-PPR Hackathon. Moscow, august 2020
  • Best solution for automated retraining of a neural network for image classification.
• Global Education Program Scholarship, 2017
  • A Russian government programme funding full-time post-graduate studies (£35,000).