See រុជា on Wiktionary
Download JSON data for រុជា meaning in All languages combined (8.8kB)
{
"etymology_templates": [
{
"args": {
"1": "km",
"2": "pi",
"3": "rujā"
},
"expansion": "Pali rujā",
"name": "bor"
},
{
"args": {
"1": "km",
"2": "sa",
"3": "रुजा"
},
"expansion": "Sanskrit रुजा (rujā)",
"name": "bor"
}
],
"etymology_text": "From Pali rujā or Sanskrit रुजा (rujā).",
"forms": [
{
"form": "ruciə",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "រុជា • (ruciə)",
"name": "km-noun"
}
],
"lang": "Khmer",
"lang_code": "km",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Khmer entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Khmer terms with non-redundant manual transliterations",
"parents": [
"Terms with non-redundant manual transliterations",
"Entry maintenance"
],
"source": "w"
},
{
"kind": "other",
"name": "Khmer terms with redundant script codes",
"parents": [
"Terms with redundant script codes",
"Entry maintenance"
],
"source": "w"
}
],
"glosses": [
"pain; disease"
],
"id": "en-រុជា-km-noun-F9pBsRTV",
"links": [
[
"poetic",
"poetic"
],
[
"pain",
"pain"
],
[
"disease",
"disease"
]
],
"raw_glosses": [
"(poetic) pain; disease"
],
"tags": [
"poetic"
]
}
],
"word": "រុជា"
}
{
"forms": [
{
"form": "feminine",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "pi-decl-noun",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"nominative",
"singular"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "រុជំ",
"roman": "rujaṃ",
"source": "declension",
"tags": [
"accusative",
"singular"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "រុជាហិ",
"roman": "rujāhi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "រុជាភិ",
"roman": "rujābhi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"dative",
"singular"
]
},
{
"form": "រុជានំ",
"roman": "rujānaṃ",
"source": "declension",
"tags": [
"dative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"ablative",
"singular"
]
},
{
"form": "រុជាហិ",
"roman": "rujāhi",
"source": "declension",
"tags": [
"ablative",
"plural"
]
},
{
"form": "រុជាភិ",
"roman": "rujābhi",
"source": "declension",
"tags": [
"ablative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"genitive",
"singular"
]
},
{
"form": "រុជានំ",
"roman": "rujānaṃ",
"source": "declension",
"tags": [
"genitive",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"locative",
"singular"
]
},
{
"form": "រុជាយំ",
"roman": "rujāyaṃ",
"source": "declension",
"tags": [
"locative",
"singular"
]
},
{
"form": "រុជាសុ",
"roman": "rujāsu",
"source": "declension",
"tags": [
"locative",
"plural"
]
},
{
"form": "រុជេ",
"roman": "ruje",
"source": "declension",
"tags": [
"singular",
"vocative"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"plural",
"vocative"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"plural",
"vocative"
]
}
],
"head_templates": [
{
"args": {
"1": "f"
},
"expansion": "រុជា f",
"name": "pi-noun"
}
],
"inflection_templates": [
{
"args": {
"g": "f"
},
"name": "pi-decl-noun"
}
],
"lang": "Pali",
"lang_code": "pi",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Khmer script",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pali entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
}
],
"form_of": [
{
"word": "rujā"
}
],
"glosses": [
"Khmer script form of rujā"
],
"id": "en-រុជា-pi-noun-jtqb-dLh",
"links": [
[
"rujā",
"rujā#Pali"
]
],
"synonyms": [
{
"tags": [
"Latin",
"character"
],
"word": "rujā"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀭"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀼"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀚"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀸"
},
{
"tags": [
"Devanagari",
"character"
],
"word": "रुजा"
},
{
"tags": [
"Bengali"
],
"word": "রুজা"
},
{
"tags": [
"Sinhalese",
"character"
],
"word": "රුජා"
},
{
"word": "ရုဇာ"
},
{
"tags": [
"Burmese",
"character"
],
"word": "ရုၹႃ"
},
{
"tags": [
"Thai",
"character"
],
"word": "รุชา"
},
{
"tags": [
"Tai-Tham",
"character"
],
"word": "ᩁᩩᨩᩣ"
},
{
"tags": [
"Lao",
"character"
],
"word": "ຣຸຊາ"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄢"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄪"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄎"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄂"
}
],
"tags": [
"Khmer",
"character",
"feminine",
"form-of"
]
}
],
"word": "រុជា"
}
{
"forms": [
{
"form": "rujā",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"g": "f"
},
"expansion": "រុជា • (rujā) stem, f",
"name": "sa-noun"
}
],
"lang": "Sanskrit",
"lang_code": "sa",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Khmer script",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Sanskrit entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
}
],
"form_of": [
{
"word": "रुजा"
}
],
"glosses": [
"Khmer script form of रुजा"
],
"id": "en-រុជា-sa-noun-eFxilZnj",
"links": [
[
"रुजा",
"रुजा#Sanskrit"
]
],
"synonyms": [
{
"tags": [
"Assamese",
"character"
],
"word": "ৰুজা"
},
{
"tags": [
"Balinese",
"character"
],
"word": "ᬭᬸᬚᬵ"
},
{
"tags": [
"Bengali"
],
"word": "রুজা"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀭"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀼"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀚"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀸"
},
{
"tags": [
"Burmese",
"character"
],
"word": "ရုဇာ"
},
{
"tags": [
"Devanagari",
"character"
],
"word": "रुजा"
},
{
"tags": [
"Gujarati",
"character"
],
"word": "રુજા"
},
{
"tags": [
"Gurmukhi",
"character"
],
"word": "ਰੁਜਾ"
},
{
"tags": [
"Javanese",
"character"
],
"word": "ꦫꦸꦗꦴ"
},
{
"tags": [
"Kannada",
"character"
],
"word": "ರುಜಾ"
},
{
"tags": [
"Lao",
"character"
],
"word": "ຣຸຊາ"
},
{
"tags": [
"Malayalam",
"character"
],
"word": "രുജാ"
},
{
"tags": [
"Modi",
"character"
],
"word": "𑘨𑘳𑘕𑘰"
},
{
"tags": [
"Mongolian"
],
"word": "ᠷᠤᠽᠠ᠋ᠠ"
},
{
"tags": [
"Newa",
"character"
],
"word": "𑐬𑐸𑐖𑐵"
},
{
"tags": [
"Odia",
"character"
],
"word": "ରୁଜା"
},
{
"tags": [
"Saurashtra",
"character"
],
"word": "ꢬꢸꢙꢵ"
},
{
"tags": [
"Sharada",
"character"
],
"word": "𑆫𑆶𑆘𑆳"
},
{
"tags": [
"Sinhalese",
"character"
],
"word": "රුජා"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚤"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚰"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚑"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚭"
},
{
"tags": [
"Tamil",
"character"
],
"word": "ருஜா"
},
{
"tags": [
"Telugu",
"character"
],
"word": "రుజా"
},
{
"tags": [
"Thai",
"character"
],
"word": "รุชา"
},
{
"tags": [
"Tibetan",
"character"
],
"word": "རུ་ཛཱ"
},
{
"tags": [
"Tirhuta",
"character"
],
"word": "𑒩𑒳𑒖𑒰"
},
{
"sense": "Bhaiksuki script",
"word": "𑰨𑰲𑰕𑰯"
},
{
"sense": "Grantha script",
"word": "𑌰𑍁𑌜𑌾"
},
{
"sense": "Kaithi script",
"word": "𑂩𑂳𑂔𑂰"
},
{
"sense": "Manchu script",
"word": "ᡵᡠᡯᠠᢇ"
},
{
"sense": "Nandinagari script",
"word": "𑧈𑧔𑦵𑧑"
},
{
"sense": "Siddham script",
"word": "𑖨𑗜𑖕𑖯"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩼"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩒"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩣"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩛"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨫"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨃"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨥"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨊"
}
],
"tags": [
"Khmer",
"character",
"form-of"
]
}
],
"word": "រុជា"
}
{
"etymology_templates": [
{
"args": {
"1": "km",
"2": "pi",
"3": "rujā"
},
"expansion": "Pali rujā",
"name": "bor"
},
{
"args": {
"1": "km",
"2": "sa",
"3": "रुजा"
},
"expansion": "Sanskrit रुजा (rujā)",
"name": "bor"
}
],
"etymology_text": "From Pali rujā or Sanskrit रुजा (rujā).",
"forms": [
{
"form": "ruciə",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "រុជា • (ruciə)",
"name": "km-noun"
}
],
"lang": "Khmer",
"lang_code": "km",
"pos": "noun",
"senses": [
{
"categories": [
"Khmer entries with incorrect language header",
"Khmer lemmas",
"Khmer nouns",
"Khmer poetic terms",
"Khmer terms borrowed from Pali",
"Khmer terms borrowed from Sanskrit",
"Khmer terms derived from Pali",
"Khmer terms derived from Sanskrit",
"Khmer terms with IPA pronunciation",
"Khmer terms with non-redundant manual transliterations",
"Khmer terms with redundant script codes"
],
"glosses": [
"pain; disease"
],
"links": [
[
"poetic",
"poetic"
],
[
"pain",
"pain"
],
[
"disease",
"disease"
]
],
"raw_glosses": [
"(poetic) pain; disease"
],
"tags": [
"poetic"
]
}
],
"word": "រុជា"
}
{
"forms": [
{
"form": "feminine",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "pi-decl-noun",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"nominative",
"singular"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "រុជំ",
"roman": "rujaṃ",
"source": "declension",
"tags": [
"accusative",
"singular"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "រុជាហិ",
"roman": "rujāhi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "រុជាភិ",
"roman": "rujābhi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"dative",
"singular"
]
},
{
"form": "រុជានំ",
"roman": "rujānaṃ",
"source": "declension",
"tags": [
"dative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"ablative",
"singular"
]
},
{
"form": "រុជាហិ",
"roman": "rujāhi",
"source": "declension",
"tags": [
"ablative",
"plural"
]
},
{
"form": "រុជាភិ",
"roman": "rujābhi",
"source": "declension",
"tags": [
"ablative",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"genitive",
"singular"
]
},
{
"form": "រុជានំ",
"roman": "rujānaṃ",
"source": "declension",
"tags": [
"genitive",
"plural"
]
},
{
"form": "រុជាយ",
"roman": "rujāya",
"source": "declension",
"tags": [
"locative",
"singular"
]
},
{
"form": "រុជាយំ",
"roman": "rujāyaṃ",
"source": "declension",
"tags": [
"locative",
"singular"
]
},
{
"form": "រុជាសុ",
"roman": "rujāsu",
"source": "declension",
"tags": [
"locative",
"plural"
]
},
{
"form": "រុជេ",
"roman": "ruje",
"source": "declension",
"tags": [
"singular",
"vocative"
]
},
{
"form": "រុជាយោ",
"roman": "rujāyo",
"source": "declension",
"tags": [
"plural",
"vocative"
]
},
{
"form": "រុជា",
"roman": "rujā",
"source": "declension",
"tags": [
"plural",
"vocative"
]
}
],
"head_templates": [
{
"args": {
"1": "f"
},
"expansion": "រុជា f",
"name": "pi-noun"
}
],
"inflection_templates": [
{
"args": {
"g": "f"
},
"name": "pi-decl-noun"
}
],
"lang": "Pali",
"lang_code": "pi",
"pos": "noun",
"senses": [
{
"categories": [
"Khmer script",
"Pali entries with incorrect language header",
"Pali feminine nouns",
"Pali lemmas",
"Pali nouns",
"Pali nouns in Khmer script"
],
"form_of": [
{
"word": "rujā"
}
],
"glosses": [
"Khmer script form of rujā"
],
"links": [
[
"rujā",
"rujā#Pali"
]
],
"tags": [
"Khmer",
"character",
"feminine",
"form-of"
]
}
],
"synonyms": [
{
"tags": [
"Latin",
"character"
],
"word": "rujā"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀭"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀼"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀚"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀸"
},
{
"tags": [
"Devanagari",
"character"
],
"word": "रुजा"
},
{
"tags": [
"Bengali"
],
"word": "রুজা"
},
{
"tags": [
"Sinhalese",
"character"
],
"word": "රුජා"
},
{
"word": "ရုဇာ"
},
{
"tags": [
"Burmese",
"character"
],
"word": "ရုၹႃ"
},
{
"tags": [
"Thai",
"character"
],
"word": "รุชา"
},
{
"tags": [
"Tai-Tham",
"character"
],
"word": "ᩁᩩᨩᩣ"
},
{
"tags": [
"Lao",
"character"
],
"word": "ຣຸຊາ"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄢"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄪"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄎"
},
{
"tags": [
"Chakma",
"character"
],
"word": "𑄂"
}
],
"word": "រុជា"
}
{
"forms": [
{
"form": "rujā",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"g": "f"
},
"expansion": "រុជា • (rujā) stem, f",
"name": "sa-noun"
}
],
"lang": "Sanskrit",
"lang_code": "sa",
"pos": "noun",
"senses": [
{
"categories": [
"Khmer script",
"Sanskrit entries with incorrect language header",
"Sanskrit feminine nouns",
"Sanskrit lemmas",
"Sanskrit nouns",
"Sanskrit nouns in Khmer script"
],
"form_of": [
{
"word": "रुजा"
}
],
"glosses": [
"Khmer script form of रुजा"
],
"links": [
[
"रुजा",
"रुजा#Sanskrit"
]
],
"tags": [
"Khmer",
"character",
"form-of"
]
}
],
"synonyms": [
{
"tags": [
"Assamese",
"character"
],
"word": "ৰুজা"
},
{
"tags": [
"Balinese",
"character"
],
"word": "ᬭᬸᬚᬵ"
},
{
"tags": [
"Bengali"
],
"word": "রুজা"
},
{
"sense": "Bhaiksuki script",
"word": "𑰨𑰲𑰕𑰯"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀭"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀼"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀚"
},
{
"tags": [
"Brahmi",
"character"
],
"word": "𑀸"
},
{
"tags": [
"Burmese",
"character"
],
"word": "ရုဇာ"
},
{
"tags": [
"Devanagari",
"character"
],
"word": "रुजा"
},
{
"tags": [
"Gujarati",
"character"
],
"word": "રુજા"
},
{
"tags": [
"Gurmukhi",
"character"
],
"word": "ਰੁਜਾ"
},
{
"sense": "Grantha script",
"word": "𑌰𑍁𑌜𑌾"
},
{
"tags": [
"Javanese",
"character"
],
"word": "ꦫꦸꦗꦴ"
},
{
"sense": "Kaithi script",
"word": "𑂩𑂳𑂔𑂰"
},
{
"tags": [
"Kannada",
"character"
],
"word": "ರುಜಾ"
},
{
"tags": [
"Lao",
"character"
],
"word": "ຣຸຊາ"
},
{
"tags": [
"Malayalam",
"character"
],
"word": "രുജാ"
},
{
"sense": "Manchu script",
"word": "ᡵᡠᡯᠠᢇ"
},
{
"tags": [
"Modi",
"character"
],
"word": "𑘨𑘳𑘕𑘰"
},
{
"tags": [
"Mongolian"
],
"word": "ᠷᠤᠽᠠ᠋ᠠ"
},
{
"sense": "Nandinagari script",
"word": "𑧈𑧔𑦵𑧑"
},
{
"tags": [
"Newa",
"character"
],
"word": "𑐬𑐸𑐖𑐵"
},
{
"tags": [
"Odia",
"character"
],
"word": "ରୁଜା"
},
{
"tags": [
"Saurashtra",
"character"
],
"word": "ꢬꢸꢙꢵ"
},
{
"tags": [
"Sharada",
"character"
],
"word": "𑆫𑆶𑆘𑆳"
},
{
"sense": "Siddham script",
"word": "𑖨𑗜𑖕𑖯"
},
{
"tags": [
"Sinhalese",
"character"
],
"word": "රුජා"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩼"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩒"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩣"
},
{
"qualifier": "Soyombo script",
"sense": "Soyombo script",
"word": "𑩛"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚤"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚰"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚑"
},
{
"tags": [
"Takri",
"character"
],
"word": "𑚭"
},
{
"tags": [
"Tamil",
"character"
],
"word": "ருஜா"
},
{
"tags": [
"Telugu",
"character"
],
"word": "రుజా"
},
{
"tags": [
"Thai",
"character"
],
"word": "รุชา"
},
{
"tags": [
"Tibetan",
"character"
],
"word": "རུ་ཛཱ"
},
{
"tags": [
"Tirhuta",
"character"
],
"word": "𑒩𑒳𑒖𑒰"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨫"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨃"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨥"
},
{
"qualifier": "Zanabazar Square script",
"sense": "Zanabazar Square script",
"word": "𑨊"
}
],
"word": "រុជា"
}
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-05-10 from the enwiktionary dump dated 2024-05-02 using wiktextract (a644e18 and edd475d). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.