{
  "version": "v0.1.0",
  "dataset": "ukrainian-frequency-lemmas",
  "subject": "A lemma-based, coverage-graded open frequency list for modern Ukrainian",
  "tier": "public",
  "provenance": "Derived aggregate counts (facts) from the UberText 2.0 lemma frequency dictionary (lang-uk, Chaplynskyi 2023). The list re-publishes counts, not the source corpus text. Rows are filtered to Ukrainian-Cyrillic-alphabetic lemmas with a linguistic Universal Dependencies POS tag; coverage is recomputed here from raw counts. This is the top 12000 lemmas, a v1 curated slice.",
  "source": {
    "name": "UberText 2.0 lemma frequency dictionary",
    "publisher": "lang-uk",
    "url": "https://lang.org.ua/static/downloads/ubertext2.0/dicts/ubertext_freq.csv.xz",
    "citation": "Chaplynskyi, D. (2023). Introducing UberText 2.0: A Corpus of Modern Ukrainian at Scale. Proc. 2nd Ukrainian NLP Workshop (UNLP), ACL.",
    "accessed": "2026-07-14"
  },
  "canonical": "/research/ukrainian-frequency",
  "wordTokenUniverse": 1495772089,
  "lemmas": 12000,
  "properNouns": 1335,
  "posHistogram": {
    "ADP": 80,
    "CCONJ": 25,
    "VERB": 2109,
    "PART": 87,
    "SCONJ": 32,
    "DET": 48,
    "NOUN": 5154,
    "PRON": 30,
    "PROPN": 1335,
    "ADV": 641,
    "ADJ": 2418,
    "NUM": 31,
    "INTJ": 10
  },
  "coverage": [
    {
      "lemmas": 100,
      "coverage": 0.3311,
      "coveragePct": 33.11
    },
    {
      "lemmas": 250,
      "coverage": 0.4243,
      "coveragePct": 42.43
    },
    {
      "lemmas": 500,
      "coverage": 0.5118,
      "coveragePct": 51.18
    },
    {
      "lemmas": 1000,
      "coverage": 0.6074,
      "coveragePct": 60.74
    },
    {
      "lemmas": 1500,
      "coverage": 0.6646,
      "coveragePct": 66.46
    },
    {
      "lemmas": 2000,
      "coverage": 0.705,
      "coveragePct": 70.5
    },
    {
      "lemmas": 3000,
      "coverage": 0.7596,
      "coveragePct": 75.96
    },
    {
      "lemmas": 4000,
      "coverage": 0.7951,
      "coveragePct": 79.51
    },
    {
      "lemmas": 5000,
      "coverage": 0.82,
      "coveragePct": 82
    },
    {
      "lemmas": 6000,
      "coverage": 0.8387,
      "coveragePct": 83.87
    },
    {
      "lemmas": 8000,
      "coverage": 0.8653,
      "coveragePct": 86.53
    },
    {
      "lemmas": 10000,
      "coverage": 0.8839,
      "coveragePct": 88.39
    },
    {
      "lemmas": 12000,
      "coverage": 0.8974,
      "coveragePct": 89.74
    }
  ],
  "milestones": [
    {
      "rank": 1000,
      "lemma": "тощо",
      "pos": "PART",
      "coveragePct": 60.74
    },
    {
      "rank": 2000,
      "lemma": "ліквідація",
      "pos": "NOUN",
      "coveragePct": 70.5
    },
    {
      "rank": 5000,
      "lemma": "перевозити",
      "pos": "VERB",
      "coveragePct": 82
    },
    {
      "rank": 10000,
      "lemma": "безсмертний",
      "pos": "ADJ",
      "coveragePct": 88.39
    }
  ],
  "checkpoints": [
    100,
    250,
    500,
    1000,
    1500,
    2000,
    3000,
    4000,
    5000,
    6000,
    8000,
    10000,
    12000
  ],
  "license": "CC-BY-4.0",
  "files": [
    {
      "file": "lemmas.json",
      "about": "The ranked lemma list: rank, lemma, UD part of speech, corpus count, document count, per-mille frequency, cumulative coverage, and the thousand-rank frequency band."
    },
    {
      "file": "lemmas.csv",
      "about": "The same ranked lemma list as CSV, for spreadsheets and scripts."
    },
    {
      "file": "lemmas.anki.tsv",
      "about": "An Anki-importable frequency deck seed: lemma, part of speech, rank, per-mille. One note per lemma, ordered most frequent first."
    },
    {
      "file": "coverage.json",
      "about": "The empirical running-text coverage curve: what share of word tokens the top N lemmas account for, at each checkpoint."
    },
    {
      "file": "coverage.csv",
      "about": "The coverage curve as CSV."
    }
  ],
  "citation": "Lawrence, J. (2026). Ukrainian Frequency: a lemma-based, coverage-graded open frequency list (v0.1.0). jakelawrence.xyz/research/ukrainian-frequency. Derived from UberText 2.0 (Chaplynskyi, 2023).",
  "sha256": {
    "lemmas.json": "116c518dc1afaaa3f3b4a73b745c02c6b5c74465e9e1d2f0a9791f81870a63bc",
    "lemmas.csv": "708db1ecb2a0f662d5760cfdb743a7cf263438c56d3bea6333befa56e00eb863",
    "lemmas.anki.tsv": "f0af3c2388aec5d39bce14100005b8d25c760a1b8e1fc8ef9b3b9b1a4dd403b4",
    "coverage.json": "f5ffbfba9bd0bfd60013f0b490a6f6f30bfa77ba1c152f762573084098a3ccb7",
    "coverage.csv": "881bba691335d4fb955c32046f863e1d0721e4bf657b29e2114f13dd41132773"
  }
}
