{
  "krdict": {
    "name": "국립국어원 한국어기초사전",
    "source": "https://krdict.korean.go.kr/download/downloadPopup",
    "snapshot": "2026-09-19",
    "license": "CC BY-SA 2.0 KR",
    "license_url": "https://creativecommons.org/licenses/by-sa/2.0/kr/",
    "entries": 53671,
    "modifications": "Selected Korean definitions, examples and supplied learning/category labels; no inferred labels."
  },
  "kaist": {
    "name": "UD Korean KAIST",
    "source": "https://github.com/UniversalDependencies/UD_Korean-Kaist",
    "revision": "5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28",
    "license": "CC BY-SA 4.0",
    "license_url": "https://creativecommons.org/licenses/by-sa/4.0/",
    "modifications": "Manual-source POS/dependencies retained. Content morphemes joined; predicate dictionary ending 다 appended by a fixed POS rule. No dates inferred."
  },
  "voa": {
    "name": "MOT VOA 한국어 뉴스",
    "source": "https://github.com/bltlab/mot",
    "release": "v1.11",
    "license": "CC BY 4.0 (MOT collection; VOA source text public domain)",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "articles": 134266,
    "excluded": {
      "non_article": 19624,
      "duplicate": 371
    },
    "modifications": "All dated article bodies; exact text duplicates removed; publication year from time_published. No model-predicted fields used."
  },
  "method": {
    "counting": "Literal non-overlapping phrase occurrences; Unicode Korean/Latin/number runs as denominator tokens. Rates per million tokens. Dialogue examples are authored examples, not recorded daily conversations. VOA topical coverage is not representative of all Korean news."
  },
  "files": [
    {
      "file": "krdict.zip",
      "url": "https://krdict.korean.go.kr/dicBatchDownload?seq=217",
      "bytes": 84486309,
      "sha256": "f9c1b9309afe66429a92cca1b2c426db25ec809d04103aca74c3a23859280df6"
    },
    {
      "file": "kor_voakorea.tgz",
      "url": "https://github.com/bltlab/mot/releases/download/v1.11/kor_voakorea.tgz",
      "bytes": 343095260,
      "sha256": "4b1ba8d20a46e491dbc21daee8951b6868391994c16d4cee2a5f4d6fe0d569a0"
    },
    {
      "file": "ko_kaist-ud-train.conllu",
      "url": "https://raw.githubusercontent.com/UniversalDependencies/UD_Korean-Kaist/5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28/ko_kaist-ud-train.conllu",
      "bytes": 34505277,
      "sha256": "6f99de7e21b8119022831afda52643dd8ff60ea386f2679c938dd7f652725d94"
    },
    {
      "file": "ko_kaist-ud-dev.conllu",
      "url": "https://raw.githubusercontent.com/UniversalDependencies/UD_Korean-Kaist/5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28/ko_kaist-ud-dev.conllu",
      "bytes": 3010966,
      "sha256": "a1ce2dceee65683c2df3b0cce96c83d01e5ff67756060b998fe01d8bc8ca4faa"
    },
    {
      "file": "ko_kaist-ud-test.conllu",
      "url": "https://raw.githubusercontent.com/UniversalDependencies/UD_Korean-Kaist/5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28/ko_kaist-ud-test.conllu",
      "bytes": 3324246,
      "sha256": "fd94dc89afb01d1f7f340a46d567e0f27ae6903a70d7b6f650b49f7427f83b97"
    },
    {
      "file": "kaist-LICENSE.txt",
      "url": "https://raw.githubusercontent.com/UniversalDependencies/UD_Korean-Kaist/5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28/LICENSE.txt",
      "bytes": 202,
      "sha256": "899b1804a12ebc090b96339614eede1b64b686721b650a71430b55b5235f7f79"
    },
    {
      "file": "kaist-README.md",
      "url": "https://raw.githubusercontent.com/UniversalDependencies/UD_Korean-Kaist/5e2cfb9a30a71e2091b6905f8f79bc2e6d4b6b28/README.md",
      "bytes": 1867,
      "sha256": "1219e86b630204112ced11c61a7922634d4f03372dce3cfb3488e8187f6ac2fb"
    },
    {
      "file": "mot-README.md",
      "url": "https://raw.githubusercontent.com/bltlab/mot/9204cad/README.md",
      "bytes": 13669,
      "sha256": "893b6a627413eb2871fc2821fd968ea7f8d8dacb8d6044a3a9d30144ea23a856"
    }
  ],
  "built_at": "2026-10-01T11:28:13.242001+00:00",
  "totals": [
    {
      "corpus": "kaist",
      "year": 0,
      "docs": 27363,
      "tokens": 310618
    },
    {
      "corpus": "krdict-dialogue",
      "year": 0,
      "docs": 63813,
      "tokens": 871918
    },
    {
      "corpus": "voa",
      "year": 2001,
      "docs": 210,
      "tokens": 62106
    },
    {
      "corpus": "voa",
      "year": 2002,
      "docs": 6086,
      "tokens": 979666
    },
    {
      "corpus": "voa",
      "year": 2003,
      "docs": 3449,
      "tokens": 1002756
    },
    {
      "corpus": "voa",
      "year": 2004,
      "docs": 4453,
      "tokens": 1037301
    },
    {
      "corpus": "voa",
      "year": 2005,
      "docs": 4703,
      "tokens": 1223416
    },
    {
      "corpus": "voa",
      "year": 2006,
      "docs": 6083,
      "tokens": 1577831
    },
    {
      "corpus": "voa",
      "year": 2007,
      "docs": 4229,
      "tokens": 903227
    },
    {
      "corpus": "voa",
      "year": 2008,
      "docs": 6467,
      "tokens": 1422202
    },
    {
      "corpus": "voa",
      "year": 2009,
      "docs": 5719,
      "tokens": 1213906
    },
    {
      "corpus": "voa",
      "year": 2010,
      "docs": 7202,
      "tokens": 1513343
    },
    {
      "corpus": "voa",
      "year": 2011,
      "docs": 8414,
      "tokens": 1972745
    },
    {
      "corpus": "voa",
      "year": 2012,
      "docs": 4646,
      "tokens": 1142858
    },
    {
      "corpus": "voa",
      "year": 2013,
      "docs": 270,
      "tokens": 72921
    },
    {
      "corpus": "voa",
      "year": 2014,
      "docs": 4379,
      "tokens": 1117693
    },
    {
      "corpus": "voa",
      "year": 2015,
      "docs": 7896,
      "tokens": 2230150
    },
    {
      "corpus": "voa",
      "year": 2016,
      "docs": 8768,
      "tokens": 2545092
    },
    {
      "corpus": "voa",
      "year": 2017,
      "docs": 7866,
      "tokens": 2447816
    },
    {
      "corpus": "voa",
      "year": 2018,
      "docs": 6752,
      "tokens": 2303756
    },
    {
      "corpus": "voa",
      "year": 2019,
      "docs": 7010,
      "tokens": 2268461
    },
    {
      "corpus": "voa",
      "year": 2020,
      "docs": 4709,
      "tokens": 1732755
    },
    {
      "corpus": "voa",
      "year": 2021,
      "docs": 2730,
      "tokens": 1061306
    },
    {
      "corpus": "voa",
      "year": 2022,
      "docs": 7305,
      "tokens": 2623369
    },
    {
      "corpus": "voa",
      "year": 2023,
      "docs": 7290,
      "tokens": 2592544
    },
    {
      "corpus": "voa",
      "year": 2024,
      "docs": 6514,
      "tokens": 2433539
    },
    {
      "corpus": "voa",
      "year": 2025,
      "docs": 1116,
      "tokens": 406715
    }
  ]
}
