See буза on Wiktionary
{
"etymology_templates": [
{
"args": {
"1": "bg",
"2": "sla-pro",
"3": "*buza"
},
"expansion": "Proto-Slavic *buza",
"name": "inh"
}
],
"etymology_text": "From Proto-Slavic *buza. Likely a substratum word, related to Albanian buzë and Romanian buză (“lip”).",
"forms": [
{
"form": "бу́за",
"tags": [
"canonical"
]
},
{
"form": "búza",
"tags": [
"romanization"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "bg-ndecl",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "бу́за",
"roman": "búza",
"source": "declension",
"tags": [
"indefinite",
"singular"
]
},
{
"form": "бу́зи",
"roman": "búzi",
"source": "declension",
"tags": [
"indefinite",
"plural"
]
},
{
"form": "бу́зата",
"roman": "búzata",
"source": "declension",
"tags": [
"definite",
"singular"
]
},
{
"form": "бу́зите",
"roman": "búzite",
"source": "declension",
"tags": [
"definite",
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "бу́за",
"2": "f"
},
"expansion": "бу́за • (búza) f",
"name": "bg-noun"
}
],
"inflection_templates": [
{
"args": {
"1": "бу́за<>"
},
"name": "bg-ndecl"
}
],
"lang": "Bulgarian",
"lang_code": "bg",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Bulgarian entries with incorrect language header",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 3 entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "bg",
"name": "Anatomy",
"orig": "bg:Anatomy",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "bg",
"name": "Face",
"orig": "bg:Face",
"parents": [],
"source": "w"
}
],
"glosses": [
"cheek (part of face)"
],
"id": "en-буза-bg-noun-ppfoXKaG",
"links": [
[
"anatomy",
"anatomy"
],
[
"cheek",
"cheek"
]
],
"raw_glosses": [
"(anatomy) cheek (part of face)"
],
"topics": [
"anatomy",
"medicine",
"sciences"
],
"wikipedia": [
"Vladimir I. Georgiev"
]
}
],
"sounds": [
{
"ipa": "[ˈbuzɐ]"
},
{
"audio": "LL-Q7918 (bul)-Kiril kovachev-буза.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/e/ed/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/e/ed/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav.ogg"
},
{
"rhymes": "-uzɐ"
}
],
"word": "буза"
}
{
"etymology_templates": [
{
"args": {
"1": "Inherited"
},
"expansion": "Inherited",
"name": "glossary"
},
{
"args": {
"1": "mk",
"2": "sla-pro",
"3": "*buza",
"4": "",
"5": "",
"g": "",
"g2": "",
"g3": "",
"id": "",
"lit": "",
"nocat": "",
"pos": "",
"sc": "",
"sort": "",
"tr": "",
"ts": ""
},
"expansion": "Proto-Slavic *buza",
"name": "inh"
},
{
"args": {
"1": "mk",
"2": "sla-pro",
"3": "*buza"
},
"expansion": "Inherited from Proto-Slavic *buza",
"name": "inh+"
}
],
"etymology_text": "Inherited from Proto-Slavic *buza.",
"forms": [
{
"form": "buza",
"tags": [
"romanization"
]
},
{
"form": "бузи",
"tags": [
"plural"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "mk-decl-noun-f",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "буза",
"roman": "buza",
"source": "declension",
"tags": [
"indefinite",
"singular"
]
},
{
"form": "бузи",
"roman": "buzi",
"source": "declension",
"tags": [
"indefinite",
"plural"
]
},
{
"form": "бузата",
"roman": "buzata",
"source": "declension",
"tags": [
"definite",
"singular",
"unspecified"
]
},
{
"form": "бузите",
"roman": "buzite",
"source": "declension",
"tags": [
"definite",
"plural",
"unspecified"
]
},
{
"form": "бузава",
"roman": "buzava",
"source": "declension",
"tags": [
"definite",
"proximal",
"singular"
]
},
{
"form": "бузиве",
"roman": "buzive",
"source": "declension",
"tags": [
"definite",
"plural",
"proximal"
]
},
{
"form": "бузана",
"roman": "buzana",
"source": "declension",
"tags": [
"definite",
"distal",
"singular"
]
},
{
"form": "бузине",
"roman": "buzine",
"source": "declension",
"tags": [
"definite",
"distal",
"plural"
]
},
{
"form": "бузо",
"roman": "buzo",
"source": "declension",
"tags": [
"singular",
"vocative"
]
},
{
"form": "бузи",
"roman": "buzi",
"source": "declension",
"tags": [
"plural",
"vocative"
]
}
],
"head_templates": [
{
"args": {
"1": "f",
"2": "бузи"
},
"expansion": "буза • (buza) f (plural бузи)",
"name": "mk-noun"
}
],
"inflection_templates": [
{
"args": {},
"name": "mk-decl-noun-f"
},
{
"args": {
"col_pl": "",
"col_pl2": "",
"col_sg": "бузје",
"col_sg2": "",
"def_dist_pl": "бузине",
"def_dist_sg": "бузана",
"def_prox_pl": "бузиве",
"def_prox_sg": "бузава",
"def_unsp_pl": "бузите",
"def_unsp_sg": "бузата",
"ind_pl": "бузи",
"ind_sg": "буза",
"n": "",
"voc_pl": "бузи",
"voc_sg": "бузо"
},
"name": "mk-decl-noun-table"
}
],
"lang": "Macedonian",
"lang_code": "mk",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Macedonian entries with incorrect language header",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with 3 entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w"
},
{
"kind": "other",
"langcode": "mk",
"name": "Face",
"orig": "mk:Face",
"parents": [],
"source": "w"
},
{
"_dis": "38 51 3 9",
"kind": "other",
"name": "Pages with 3 entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "36 49 2 13",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"lip"
],
"id": "en-буза-mk-noun-isHvU4HK",
"links": [
[
"lip",
"lip"
]
],
"raw_glosses": [
"(dialectal) lip"
],
"tags": [
"dialectal"
]
}
],
"sounds": [
{
"ipa": "[ˈbuza]"
}
],
"word": "буза"
}
{
"forms": [
{
"form": "буза́",
"tags": [
"canonical"
]
},
{
"form": "buzá",
"tags": [
"romanization"
]
},
{
"form": "бузы́",
"tags": [
"genitive"
]
},
{
"form": "бузы́",
"tags": [
"nominative",
"plural"
]
},
{
"form": "буз",
"tags": [
"genitive",
"plural"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "ru-noun-table",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "hard-stem",
"source": "declension",
"tags": [
"class"
]
},
{
"form": "accent-b",
"source": "declension",
"tags": [
"class"
]
},
{
"form": "буза́",
"roman": "buzá",
"source": "declension",
"tags": [
"nominative",
"singular"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"genitive",
"singular"
]
},
{
"form": "бу́з",
"roman": "búz",
"source": "declension",
"tags": [
"genitive",
"plural"
]
},
{
"form": "бузе́",
"roman": "buzé",
"source": "declension",
"tags": [
"dative",
"singular"
]
},
{
"form": "буза́м",
"roman": "buzám",
"source": "declension",
"tags": [
"dative",
"plural"
]
},
{
"form": "бузу́",
"roman": "buzú",
"source": "declension",
"tags": [
"accusative",
"singular"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "бузо́й",
"roman": "buzój",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "бузо́ю",
"roman": "buzóju",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "буза́ми",
"roman": "buzámi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "бузе́",
"roman": "buzé",
"source": "declension",
"tags": [
"prepositional",
"singular"
]
},
{
"form": "буза́х",
"roman": "buzáx",
"source": "declension",
"tags": [
"plural",
"prepositional"
]
}
],
"head_templates": [
{
"args": {
"1": "буза́"
},
"expansion": "буза́ • (buzá) f inan (genitive бузы́, nominative plural бузы́, genitive plural буз)",
"name": "ru-noun+"
}
],
"lang": "Russian",
"lang_code": "ru",
"pos": "noun",
"related": [
{
"_dis1": "0 0",
"roman": "buzitʹ",
"word": "бузить"
},
{
"_dis1": "0 0",
"roman": "buzotjór",
"word": "бузотёр"
}
],
"senses": [
{
"categories": [
{
"_dis": "45 55",
"kind": "other",
"name": "Russian nouns with accent pattern b",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"noisy row, uproar, fuss"
],
"id": "en-буза-ru-noun-eWEOjzWl",
"links": [
[
"row",
"row"
],
[
"uproar",
"uproar"
],
[
"fuss",
"fuss"
]
],
"synonyms": [
{
"word": "шум"
},
{
"word": "сканда́л"
}
]
},
{
"categories": [
{
"_dis": "30 70",
"kind": "other",
"name": "Russian entries with incorrect language header",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "36 64",
"kind": "other",
"name": "Russian links with redundant alt parameters",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "38 62",
"kind": "other",
"name": "Russian links with redundant wikilinks",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "45 55",
"kind": "other",
"name": "Russian nouns with accent pattern b",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "6 94",
"kind": "other",
"langcode": "ru",
"name": "Beverages",
"orig": "ru:Beverages",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"boza (a fermented, malted beverage made from millet, buckwheat, oats, or barley, popular in the Crimea and Caucasus. It has a thick consistency and a low alcohol content, usually around 4–6%, and has a slightly acidic sweet flavor)"
],
"id": "en-буза-ru-noun-G~y996IF"
}
],
"sounds": [
{
"ipa": "[bʊˈza]"
}
],
"wikipedia": [
"ru:буза"
],
"word": "буза"
}
{
"categories": [
"Pages with 3 entries",
"Pages with entries",
"ru:Beverages"
],
"etymology_templates": [
{
"args": {
"1": "bg",
"2": "sla-pro",
"3": "*buza"
},
"expansion": "Proto-Slavic *buza",
"name": "inh"
}
],
"etymology_text": "From Proto-Slavic *buza. Likely a substratum word, related to Albanian buzë and Romanian buză (“lip”).",
"forms": [
{
"form": "бу́за",
"tags": [
"canonical"
]
},
{
"form": "búza",
"tags": [
"romanization"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "bg-ndecl",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "бу́за",
"roman": "búza",
"source": "declension",
"tags": [
"indefinite",
"singular"
]
},
{
"form": "бу́зи",
"roman": "búzi",
"source": "declension",
"tags": [
"indefinite",
"plural"
]
},
{
"form": "бу́зата",
"roman": "búzata",
"source": "declension",
"tags": [
"definite",
"singular"
]
},
{
"form": "бу́зите",
"roman": "búzite",
"source": "declension",
"tags": [
"definite",
"plural"
]
}
],
"head_templates": [
{
"args": {
"1": "бу́за",
"2": "f"
},
"expansion": "бу́за • (búza) f",
"name": "bg-noun"
}
],
"inflection_templates": [
{
"args": {
"1": "бу́за<>"
},
"name": "bg-ndecl"
}
],
"lang": "Bulgarian",
"lang_code": "bg",
"pos": "noun",
"senses": [
{
"categories": [
"Bulgarian entries with incorrect language header",
"Bulgarian feminine nouns",
"Bulgarian lemmas",
"Bulgarian nouns",
"Bulgarian terms derived from Proto-Slavic",
"Bulgarian terms derived from substrate languages",
"Bulgarian terms inherited from Proto-Slavic",
"Bulgarian terms with IPA pronunciation",
"Pages with 3 entries",
"Pages with entries",
"Rhymes:Bulgarian/uzɐ",
"Rhymes:Bulgarian/uzɐ/2 syllables",
"bg:Anatomy",
"bg:Face"
],
"glosses": [
"cheek (part of face)"
],
"links": [
[
"anatomy",
"anatomy"
],
[
"cheek",
"cheek"
]
],
"raw_glosses": [
"(anatomy) cheek (part of face)"
],
"topics": [
"anatomy",
"medicine",
"sciences"
],
"wikipedia": [
"Vladimir I. Georgiev"
]
}
],
"sounds": [
{
"ipa": "[ˈbuzɐ]"
},
{
"audio": "LL-Q7918 (bul)-Kiril kovachev-буза.wav",
"mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/e/ed/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav.mp3",
"ogg_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/e/ed/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav/LL-Q7918_%28bul%29-Kiril_kovachev-%D0%B1%D1%83%D0%B7%D0%B0.wav.ogg"
},
{
"rhymes": "-uzɐ"
}
],
"word": "буза"
}
{
"categories": [
"Pages with 3 entries",
"Pages with entries",
"ru:Beverages"
],
"etymology_templates": [
{
"args": {
"1": "Inherited"
},
"expansion": "Inherited",
"name": "glossary"
},
{
"args": {
"1": "mk",
"2": "sla-pro",
"3": "*buza",
"4": "",
"5": "",
"g": "",
"g2": "",
"g3": "",
"id": "",
"lit": "",
"nocat": "",
"pos": "",
"sc": "",
"sort": "",
"tr": "",
"ts": ""
},
"expansion": "Proto-Slavic *buza",
"name": "inh"
},
{
"args": {
"1": "mk",
"2": "sla-pro",
"3": "*buza"
},
"expansion": "Inherited from Proto-Slavic *buza",
"name": "inh+"
}
],
"etymology_text": "Inherited from Proto-Slavic *buza.",
"forms": [
{
"form": "buza",
"tags": [
"romanization"
]
},
{
"form": "бузи",
"tags": [
"plural"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "mk-decl-noun-f",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "буза",
"roman": "buza",
"source": "declension",
"tags": [
"indefinite",
"singular"
]
},
{
"form": "бузи",
"roman": "buzi",
"source": "declension",
"tags": [
"indefinite",
"plural"
]
},
{
"form": "бузата",
"roman": "buzata",
"source": "declension",
"tags": [
"definite",
"singular",
"unspecified"
]
},
{
"form": "бузите",
"roman": "buzite",
"source": "declension",
"tags": [
"definite",
"plural",
"unspecified"
]
},
{
"form": "бузава",
"roman": "buzava",
"source": "declension",
"tags": [
"definite",
"proximal",
"singular"
]
},
{
"form": "бузиве",
"roman": "buzive",
"source": "declension",
"tags": [
"definite",
"plural",
"proximal"
]
},
{
"form": "бузана",
"roman": "buzana",
"source": "declension",
"tags": [
"definite",
"distal",
"singular"
]
},
{
"form": "бузине",
"roman": "buzine",
"source": "declension",
"tags": [
"definite",
"distal",
"plural"
]
},
{
"form": "бузо",
"roman": "buzo",
"source": "declension",
"tags": [
"singular",
"vocative"
]
},
{
"form": "бузи",
"roman": "buzi",
"source": "declension",
"tags": [
"plural",
"vocative"
]
}
],
"head_templates": [
{
"args": {
"1": "f",
"2": "бузи"
},
"expansion": "буза • (buza) f (plural бузи)",
"name": "mk-noun"
}
],
"inflection_templates": [
{
"args": {},
"name": "mk-decl-noun-f"
},
{
"args": {
"col_pl": "",
"col_pl2": "",
"col_sg": "бузје",
"col_sg2": "",
"def_dist_pl": "бузине",
"def_dist_sg": "бузана",
"def_prox_pl": "бузиве",
"def_prox_sg": "бузава",
"def_unsp_pl": "бузите",
"def_unsp_sg": "бузата",
"ind_pl": "бузи",
"ind_sg": "буза",
"n": "",
"voc_pl": "бузи",
"voc_sg": "бузо"
},
"name": "mk-decl-noun-table"
}
],
"lang": "Macedonian",
"lang_code": "mk",
"pos": "noun",
"senses": [
{
"categories": [
"Macedonian 2-syllable words",
"Macedonian dialectal terms",
"Macedonian entries with incorrect language header",
"Macedonian feminine nouns",
"Macedonian lemmas",
"Macedonian nouns",
"Macedonian paroxytone terms",
"Macedonian terms derived from Proto-Slavic",
"Macedonian terms inherited from Proto-Slavic",
"Macedonian terms with IPA pronunciation",
"Pages with 3 entries",
"Pages with entries",
"mk:Face"
],
"glosses": [
"lip"
],
"links": [
[
"lip",
"lip"
]
],
"raw_glosses": [
"(dialectal) lip"
],
"tags": [
"dialectal"
]
}
],
"sounds": [
{
"ipa": "[ˈbuza]"
}
],
"word": "буза"
}
{
"categories": [
"Pages with 3 entries",
"Pages with entries",
"Russian 2-syllable words",
"Russian entries with incorrect language header",
"Russian feminine nouns",
"Russian hard-stem feminine-form accent-b nouns",
"Russian hard-stem feminine-form nouns",
"Russian inanimate nouns",
"Russian lemmas",
"Russian links with redundant alt parameters",
"Russian links with redundant wikilinks",
"Russian nouns",
"Russian nouns with accent pattern b",
"Russian terms with IPA pronunciation",
"ru:Beverages"
],
"forms": [
{
"form": "буза́",
"tags": [
"canonical"
]
},
{
"form": "buzá",
"tags": [
"romanization"
]
},
{
"form": "бузы́",
"tags": [
"genitive"
]
},
{
"form": "бузы́",
"tags": [
"nominative",
"plural"
]
},
{
"form": "буз",
"tags": [
"genitive",
"plural"
]
},
{
"form": "no-table-tags",
"source": "declension",
"tags": [
"table-tags"
]
},
{
"form": "ru-noun-table",
"source": "declension",
"tags": [
"inflection-template"
]
},
{
"form": "hard-stem",
"source": "declension",
"tags": [
"class"
]
},
{
"form": "accent-b",
"source": "declension",
"tags": [
"class"
]
},
{
"form": "буза́",
"roman": "buzá",
"source": "declension",
"tags": [
"nominative",
"singular"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"nominative",
"plural"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"genitive",
"singular"
]
},
{
"form": "бу́з",
"roman": "búz",
"source": "declension",
"tags": [
"genitive",
"plural"
]
},
{
"form": "бузе́",
"roman": "buzé",
"source": "declension",
"tags": [
"dative",
"singular"
]
},
{
"form": "буза́м",
"roman": "buzám",
"source": "declension",
"tags": [
"dative",
"plural"
]
},
{
"form": "бузу́",
"roman": "buzú",
"source": "declension",
"tags": [
"accusative",
"singular"
]
},
{
"form": "бузы́",
"roman": "buzý",
"source": "declension",
"tags": [
"accusative",
"plural"
]
},
{
"form": "бузо́й",
"roman": "buzój",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "бузо́ю",
"roman": "buzóju",
"source": "declension",
"tags": [
"instrumental",
"singular"
]
},
{
"form": "буза́ми",
"roman": "buzámi",
"source": "declension",
"tags": [
"instrumental",
"plural"
]
},
{
"form": "бузе́",
"roman": "buzé",
"source": "declension",
"tags": [
"prepositional",
"singular"
]
},
{
"form": "буза́х",
"roman": "buzáx",
"source": "declension",
"tags": [
"plural",
"prepositional"
]
}
],
"head_templates": [
{
"args": {
"1": "буза́"
},
"expansion": "буза́ • (buzá) f inan (genitive бузы́, nominative plural бузы́, genitive plural буз)",
"name": "ru-noun+"
}
],
"lang": "Russian",
"lang_code": "ru",
"pos": "noun",
"related": [
{
"roman": "buzitʹ",
"word": "бузить"
},
{
"roman": "buzotjór",
"word": "бузотёр"
}
],
"senses": [
{
"glosses": [
"noisy row, uproar, fuss"
],
"links": [
[
"row",
"row"
],
[
"uproar",
"uproar"
],
[
"fuss",
"fuss"
]
],
"synonyms": [
{
"word": "шум"
},
{
"word": "сканда́л"
}
]
},
{
"glosses": [
"boza (a fermented, malted beverage made from millet, buckwheat, oats, or barley, popular in the Crimea and Caucasus. It has a thick consistency and a low alcohol content, usually around 4–6%, and has a slightly acidic sweet flavor)"
]
}
],
"sounds": [
{
"ipa": "[bʊˈza]"
}
],
"wikipedia": [
"ru:буза"
],
"word": "буза"
}
Download raw JSONL data for буза meaning in All languages combined (8.7kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2025-06-16 from the enwiktionary dump dated 2025-06-01 using wiktextract (074e7de and f1c2b61). 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.