Skip to content
View ZavarOvek's full-sized avatar
🌴
Born to dilly, forced to dally.
🌴
Born to dilly, forced to dally.
  • 15:05 (UTC +03:00)

Block or report ZavarOvek

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
ZavarOvek/README.md

Hi, I'm Yurii

NLP and text-data engineer (Python). BA in applied/computational linguistics, Taras Shevchenko National University of Kyiv. I build text-processing tools end to end: data collection → cleaning → corpus building → retrieval and evaluation. Working languages: Ukrainian and English.

What each project demonstrates

Project What it shows
lyrics-semantic-search Hybrid retrieval (dense embeddings + BM25, fused by Reciprocal Rank Fusion) over a ~30k-song corpus. Cached offline build pipeline, pluggable embedders and index backends, 176 tests, 100% coverage of the pure core
bg3-corpus 186k-pair EN–UK parallel corpus built from game localization files; MT evaluation across 5 metrics (BLEU, METEOR, TER, ChrF++, BERTScore). BA thesis
longcat_discord_bot Production-style Discord bot: LLM chat with a tool loop and long-term memory, moderation, reminders. SQLite, 213 tests
tg-corpus Telegram channel → clean, deduplicated text corpus. Two-stage design: API fetch, then a fully offline cleaning pipeline with auto-detected sign-off stripping
ua-freq-dict Frequency dictionaries for Ukrainian: wordforms, lemmas, POS, n-grams (pymorphy3). Exports to CSV / XLSX / SQLite
tf-idf-summariser Extractive TF-IDF summarization for Ukrainian and English — deterministic, no model downloads

Every repository: bilingual README (EN / UK), MIT license, tests in CI.

Pinned Loading

  1. lyrics-semantic-search lyrics-semantic-search Public

    Semantic search over song lyrics: dense embedding sarch, lexical (BM25) search, and a hybrid fused by rnk, and not raw score. Full offline indexing pipeline though online query serving.

    Python

  2. bg3-corpus bg3-corpus Public

    EN-UK parallel corpus pipeline built from Baldur's Gate 3 localization files: 186k aligned pairs, 7 text types, Gemini API translation and MT evaluation (BLEU, METEOR, TER, ChrF++, BERTScore). BA t…

    Python

  3. longcat_discord_bot longcat_discord_bot Public

    Personal Discord bot in Python: LLM chat with tool loop and long-term memory + local-database advisor. Moderation, reminders, polls, levels. SQLite, 213 tests.

    Python

  4. tf-idf-summariser tf-idf-summariser Public

    Extractive TF-IDF summarizer for Ukrainian and English. Auto language detection, no model downloads, deterministic output. CLI + Python library on scikit-learn.

    Python

  5. tg-corpus tg-corpus Public

    Turn a public Telegram channel into a clean, deduplicated text corpus. Two-stage design: Telethon fetch + fully offline cleaning pipeline with auto-detected sign-off stripping. Exports JSONL / CSV …

    Python

  6. ua-freq-dict ua-freq-dict Public

    Frequency dictionaries for Ukrainian text: wordforms, lemmas, POS and n-grams with per-subsample counts for statistical analysis. CLI + Python library, exports to CSV / XLSX / SQLite. Built on pymo…

    Python