Skip to content
View kanincityy's full-sized avatar

Highlights

  • Pro

Block or report kanincityy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kanincityy/README.md

Hi, I’m Tatiana!

I'm a multilingual NLP and AI enthusiast working as a Prompt Engineer / Junior Data Scientist at Wyser. While also completing my MSc in Language Sciences: Technology of Language and Speech at UCL. I specialise in machine learning for language and speech, with a focus on low-resource NLP, speech emotion recognition, and LLM-powered applications.

My mission is to build human-centred AI systems that make language technologies more inclusive, accessible, and responsible.


Research & Technical Interests

  • Multilingual NLP: Cross-lingual transfer learning, hate speech detection, low-resource language tools
  • Speech Technology: Emotion recognition, noise-robust models, assistive tech for accessibility
  • LLMs & Prompt Engineering: LLM integrations for structured-to-natural language generation
  • Ethical AI: Fairness, bias mitigation, and inclusive language modeling

Tools & Skills

Languages & Libraries: Python, R, SQL, PyTorch, TensorFlow, Hugging Face, Scikit-learn
NLP & Speech: Transformers, SpaCy, Librosa, Praat, Seaborn, Matplotlib
Other: Git, Docker, MLOps (learning)


Current Projects

  • SER in Noise: Speech emotion recognition under white noise (MSc dissertation)
  • Misogyny Detection: Low-resource Swedish misogyny classification with multilingual Transformers
  • Smart Writing Coach: LLM-based application that generates essay feedback for EFL students

Currently Exploring

  • Advanced NLP architectures (LLMs, Retrieval-Augmented Generation)
  • AI fairness metrics and debiasing strategies
  • Lightweight model deployment (FastAPI, Streamlit, Docker)

Let’s Connect!

  • Based in the UK | SE
  • LinkedIn
  • Portfolio: Coming Soon

Fun Facts

  • Fluent in 5 languages (Russian, Spanish, English, Catalan, French)
  • Occasional Advent of Code participant
  • Enjoy reading (and sometimes writing!) fiction and poetry

Thanks for visiting & happy coding! 🐇

Pinned Loading

  1. misogyny_detection_transformers misogyny_detection_transformers Public

    Building an Effective Misogyny Detection Classifier for Low-Resource Languages

  2. char_lstm_text_autocompletion char_lstm_text_autocompletion Public

    Character-Level Text Auto-Completion with LSTMs

  3. gpt_vet_discharge_note_generator gpt_vet_discharge_note_generator Public

    Python

  4. smart_writing_coach smart_writing_coach Public

    Python