See 不覺 on Wiktionary
Download JSON data for 不覺 meaning in All languages combined (7.2kB)
{
"derived": [
{
"_dis1": "0 0",
"roman": "bùzhī-bùjué",
"word": "不知不覺"
},
{
"_dis1": "0 0",
"roman": "bùzhī-bùjué",
"word": "不知不觉"
}
],
"head_templates": [
{
"args": {},
"expansion": "不覺",
"name": "zh-verb"
}
],
"lang": "Chinese",
"lang_code": "zh",
"pos": "verb",
"senses": [
{
"glosses": [
"to be unconscious"
],
"id": "en-不覺-zh-verb-VDs8T9E8",
"links": [
[
"unconscious",
"unconscious"
]
]
},
{
"glosses": [
"to be unwitting; to not have noticed; to be unaware"
],
"id": "en-不覺-zh-verb-kS0I8xtv",
"links": [
[
"unwitting",
"unwitting"
],
[
"notice",
"notice"
],
[
"unaware",
"unaware"
]
]
}
],
"sounds": [
{
"tags": [
"Mandarin",
"Pinyin"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Cantonese",
"Jyutping"
],
"zh-pron": "bat¹ gok³"
},
{
"zh-pron": "put-kak"
},
{
"tags": [
"Hanyu-Pinyin",
"Mandarin",
"standard"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo",
"standard"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Mandarin",
"Tongyong-Pinyin",
"standard"
],
"zh-pron": "bùjyué"
},
{
"tags": [
"Mandarin",
"Wade-Giles",
"standard"
],
"zh-pron": "pu⁴-chüeh²"
},
{
"tags": [
"Mandarin",
"Yale",
"standard"
],
"zh-pron": "bù-jywé"
},
{
"tags": [
"Gwoyeu-Romatsyh",
"Mandarin",
"standard"
],
"zh-pron": "bujyue"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "буцзюэ"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "buczjue"
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/",
"tags": [
"Mandarin",
"Sinological-IPA",
"standard"
]
},
{
"tags": [
"Cantonese",
"Yale"
],
"zh-pron": "bāt gok"
},
{
"tags": [
"Cantonese",
"Pinyin"
],
"zh-pron": "bat⁷ gok⁸"
},
{
"tags": [
"Cantonese",
"Guangdong-Romanization"
],
"zh-pron": "bed¹ gog³"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/",
"tags": [
"Cantonese",
"Sinological-IPA"
]
},
{
"tags": [
"Hokkien",
"POJ"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Tai-lo"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Phofsit-Daibuun"
],
"zh-pron": "putkag"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Xiamen"
]
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/",
"tags": [
"Hokkien",
"Quanzhou"
]
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/",
"tags": [
"Hokkien",
"Zhangzhou"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Taipei"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Kaohsiung"
]
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/"
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
}
],
"word": "不覺"
}
{
"descendants": [
{
"depth": 0,
"templates": [
{
"args": {
"1": "zh",
"2": "不覺"
},
"expansion": "不覺",
"name": "lang"
},
{
"args": {
"1": "ja",
"2": "-",
"bor": "1"
},
"expansion": "→ Japanese:",
"name": "desc"
},
{
"args": {
"1": "不覚",
"2": "ふかく",
"gloss": ""
},
"expansion": "不覚(ふかく) (fukaku)",
"name": "ja-r"
},
{
"args": {
"1": "不覺",
"2": "ふかく",
"3": "",
"4": "",
"5": "",
"6": "",
"h": "不覺",
"j2": "",
"j2t": "",
"j3": "",
"j3t": "",
"j4": "",
"j4t": "",
"jdesc": "",
"jje2": "",
"jje2t": "",
"jje3": "",
"jje3t": "",
"jje4": "",
"jje4t": "",
"jjedesc": "",
"jjet": "",
"jt": "",
"k2": "",
"k2t": "",
"k3": "",
"k3t": "",
"k4": "",
"k4t": "",
"kdesc": "",
"kt": "",
"o": "不覺",
"o2": "",
"o2t": "",
"o3": "",
"o3t": "",
"o4": "",
"o4t": "",
"odesc": "",
"ot": "",
"s": "不覚",
"v": "不覺",
"v2": "",
"v2t": "",
"v3": "",
"v3t": "",
"v4": "",
"v4t": "",
"vdesc": "",
"vt": ""
},
"expansion": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)",
"name": "CJKV/code"
},
{
"args": {
"1": "",
"2": "ふかく",
"s": "不覚"
},
"expansion": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)",
"name": "CJKV"
}
],
"text": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)"
}
],
"head_templates": [
{
"args": {
"1": "zh",
"2": "adverb"
},
"expansion": "不覺",
"name": "head"
}
],
"lang": "Chinese",
"lang_code": "zh",
"pos": "adv",
"senses": [
{
"categories": [
{
"_dis": "68 8 24",
"kind": "other",
"name": "Chinese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "50 31 19",
"kind": "other",
"name": "Intermediate Mandarin",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"can't help but (do something)"
],
"id": "en-不覺-zh-adv-3-VpcY8n",
"links": [
[
"can't help",
"can't help"
]
],
"synonyms": [
{
"roman": "bùyóude",
"word": "不由得"
},
{
"roman": "bùjīn",
"word": "不禁"
}
]
}
],
"sounds": [
{
"tags": [
"Mandarin",
"Pinyin"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Cantonese",
"Jyutping"
],
"zh-pron": "bat¹ gok³"
},
{
"zh-pron": "put-kak"
},
{
"tags": [
"Hanyu-Pinyin",
"Mandarin",
"standard"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo",
"standard"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Mandarin",
"Tongyong-Pinyin",
"standard"
],
"zh-pron": "bùjyué"
},
{
"tags": [
"Mandarin",
"Wade-Giles",
"standard"
],
"zh-pron": "pu⁴-chüeh²"
},
{
"tags": [
"Mandarin",
"Yale",
"standard"
],
"zh-pron": "bù-jywé"
},
{
"tags": [
"Gwoyeu-Romatsyh",
"Mandarin",
"standard"
],
"zh-pron": "bujyue"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "буцзюэ"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "buczjue"
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/",
"tags": [
"Mandarin",
"Sinological-IPA",
"standard"
]
},
{
"tags": [
"Cantonese",
"Yale"
],
"zh-pron": "bāt gok"
},
{
"tags": [
"Cantonese",
"Pinyin"
],
"zh-pron": "bat⁷ gok⁸"
},
{
"tags": [
"Cantonese",
"Guangdong-Romanization"
],
"zh-pron": "bed¹ gog³"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/",
"tags": [
"Cantonese",
"Sinological-IPA"
]
},
{
"tags": [
"Hokkien",
"POJ"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Tai-lo"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Phofsit-Daibuun"
],
"zh-pron": "putkag"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Xiamen"
]
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/",
"tags": [
"Hokkien",
"Quanzhou"
]
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/",
"tags": [
"Hokkien",
"Zhangzhou"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Taipei"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Kaohsiung"
]
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/"
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
}
],
"word": "不覺"
}
{
"head_templates": [
{
"args": {
"1": "vi",
"2": "adverb",
"3": "",
"4": "",
"head": "",
"tr": ""
},
"expansion": "不覺",
"name": "head"
},
{
"args": {
"sc": "Hani"
},
"expansion": "不覺",
"name": "vi-adv"
}
],
"lang": "Vietnamese",
"lang_code": "vi",
"pos": "adv",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Vietnamese Chữ Hán",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Vietnamese adverbs in Han script",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Vietnamese entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w"
}
],
"glosses": [
"chữ Hán form of bất giác."
],
"id": "en-不覺-vi-adv-tF9tRijG",
"links": [
[
"chữ Hán",
"chữ Hán#Vietnamese"
],
[
"bất giác",
"bất giác#Vietnamese"
]
]
}
],
"word": "不覺"
}
{
"categories": [
"Chinese adverbs",
"Chinese entries with incorrect language header",
"Chinese lemmas",
"Chinese terms with IPA pronunciation",
"Chinese verbs",
"Intermediate Mandarin"
],
"derived": [
{
"roman": "bùzhī-bùjué",
"word": "不知不覺"
},
{
"roman": "bùzhī-bùjué",
"word": "不知不觉"
}
],
"head_templates": [
{
"args": {},
"expansion": "不覺",
"name": "zh-verb"
}
],
"lang": "Chinese",
"lang_code": "zh",
"pos": "verb",
"senses": [
{
"glosses": [
"to be unconscious"
],
"links": [
[
"unconscious",
"unconscious"
]
]
},
{
"glosses": [
"to be unwitting; to not have noticed; to be unaware"
],
"links": [
[
"unwitting",
"unwitting"
],
[
"notice",
"notice"
],
[
"unaware",
"unaware"
]
]
}
],
"sounds": [
{
"tags": [
"Mandarin",
"Pinyin"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Cantonese",
"Jyutping"
],
"zh-pron": "bat¹ gok³"
},
{
"zh-pron": "put-kak"
},
{
"tags": [
"Hanyu-Pinyin",
"Mandarin",
"standard"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo",
"standard"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Mandarin",
"Tongyong-Pinyin",
"standard"
],
"zh-pron": "bùjyué"
},
{
"tags": [
"Mandarin",
"Wade-Giles",
"standard"
],
"zh-pron": "pu⁴-chüeh²"
},
{
"tags": [
"Mandarin",
"Yale",
"standard"
],
"zh-pron": "bù-jywé"
},
{
"tags": [
"Gwoyeu-Romatsyh",
"Mandarin",
"standard"
],
"zh-pron": "bujyue"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "буцзюэ"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "buczjue"
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/",
"tags": [
"Mandarin",
"Sinological-IPA",
"standard"
]
},
{
"tags": [
"Cantonese",
"Yale"
],
"zh-pron": "bāt gok"
},
{
"tags": [
"Cantonese",
"Pinyin"
],
"zh-pron": "bat⁷ gok⁸"
},
{
"tags": [
"Cantonese",
"Guangdong-Romanization"
],
"zh-pron": "bed¹ gog³"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/",
"tags": [
"Cantonese",
"Sinological-IPA"
]
},
{
"tags": [
"Hokkien",
"POJ"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Tai-lo"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Phofsit-Daibuun"
],
"zh-pron": "putkag"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Xiamen"
]
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/",
"tags": [
"Hokkien",
"Quanzhou"
]
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/",
"tags": [
"Hokkien",
"Zhangzhou"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Taipei"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Kaohsiung"
]
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/"
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
}
],
"word": "不覺"
}
{
"categories": [
"Chinese adverbs",
"Chinese entries with incorrect language header",
"Chinese lemmas",
"Chinese terms with IPA pronunciation",
"Chinese verbs",
"Intermediate Mandarin"
],
"descendants": [
{
"depth": 0,
"templates": [
{
"args": {
"1": "zh",
"2": "不覺"
},
"expansion": "不覺",
"name": "lang"
},
{
"args": {
"1": "ja",
"2": "-",
"bor": "1"
},
"expansion": "→ Japanese:",
"name": "desc"
},
{
"args": {
"1": "不覚",
"2": "ふかく",
"gloss": ""
},
"expansion": "不覚(ふかく) (fukaku)",
"name": "ja-r"
},
{
"args": {
"1": "不覺",
"2": "ふかく",
"3": "",
"4": "",
"5": "",
"6": "",
"h": "不覺",
"j2": "",
"j2t": "",
"j3": "",
"j3t": "",
"j4": "",
"j4t": "",
"jdesc": "",
"jje2": "",
"jje2t": "",
"jje3": "",
"jje3t": "",
"jje4": "",
"jje4t": "",
"jjedesc": "",
"jjet": "",
"jt": "",
"k2": "",
"k2t": "",
"k3": "",
"k3t": "",
"k4": "",
"k4t": "",
"kdesc": "",
"kt": "",
"o": "不覺",
"o2": "",
"o2t": "",
"o3": "",
"o3t": "",
"o4": "",
"o4t": "",
"odesc": "",
"ot": "",
"s": "不覚",
"v": "不覺",
"v2": "",
"v2t": "",
"v3": "",
"v3t": "",
"v4": "",
"v4t": "",
"vdesc": "",
"vt": ""
},
"expansion": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)",
"name": "CJKV/code"
},
{
"args": {
"1": "",
"2": "ふかく",
"s": "不覚"
},
"expansion": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)",
"name": "CJKV"
}
],
"text": "Sino-Xenic (不覺):\n* → Japanese: 不覚(ふかく) (fukaku)"
}
],
"head_templates": [
{
"args": {
"1": "zh",
"2": "adverb"
},
"expansion": "不覺",
"name": "head"
}
],
"lang": "Chinese",
"lang_code": "zh",
"pos": "adv",
"senses": [
{
"glosses": [
"can't help but (do something)"
],
"links": [
[
"can't help",
"can't help"
]
]
}
],
"sounds": [
{
"tags": [
"Mandarin",
"Pinyin"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Cantonese",
"Jyutping"
],
"zh-pron": "bat¹ gok³"
},
{
"zh-pron": "put-kak"
},
{
"tags": [
"Hanyu-Pinyin",
"Mandarin",
"standard"
],
"zh-pron": "bùjué"
},
{
"tags": [
"Mandarin",
"bopomofo",
"standard"
],
"zh-pron": "ㄅㄨˋ ㄐㄩㄝˊ"
},
{
"tags": [
"Mandarin",
"Tongyong-Pinyin",
"standard"
],
"zh-pron": "bùjyué"
},
{
"tags": [
"Mandarin",
"Wade-Giles",
"standard"
],
"zh-pron": "pu⁴-chüeh²"
},
{
"tags": [
"Mandarin",
"Yale",
"standard"
],
"zh-pron": "bù-jywé"
},
{
"tags": [
"Gwoyeu-Romatsyh",
"Mandarin",
"standard"
],
"zh-pron": "bujyue"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "буцзюэ"
},
{
"tags": [
"Mandarin",
"Palladius",
"standard"
],
"zh-pron": "buczjue"
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/",
"tags": [
"Mandarin",
"Sinological-IPA",
"standard"
]
},
{
"tags": [
"Cantonese",
"Yale"
],
"zh-pron": "bāt gok"
},
{
"tags": [
"Cantonese",
"Pinyin"
],
"zh-pron": "bat⁷ gok⁸"
},
{
"tags": [
"Cantonese",
"Guangdong-Romanization"
],
"zh-pron": "bed¹ gog³"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/",
"tags": [
"Cantonese",
"Sinological-IPA"
]
},
{
"tags": [
"Hokkien",
"POJ"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Tai-lo"
],
"zh-pron": "put-kak"
},
{
"tags": [
"Hokkien",
"Phofsit-Daibuun"
],
"zh-pron": "putkag"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Xiamen"
]
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/",
"tags": [
"Hokkien",
"Quanzhou"
]
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/",
"tags": [
"Hokkien",
"Zhangzhou"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Taipei"
]
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/",
"tags": [
"Hokkien",
"Kaohsiung"
]
},
{
"ipa": "/pu⁵¹ t͡ɕy̯ɛ³⁵/"
},
{
"ipa": "/pɐt̚⁵ kɔːk̚³/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚⁵⁻²⁴ kak̚⁵/"
},
{
"ipa": "/put̚³²⁻⁵ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
},
{
"ipa": "/put̚³²⁻⁴ kak̚³²/"
}
],
"synonyms": [
{
"roman": "bùyóude",
"word": "不由得"
},
{
"roman": "bùjīn",
"word": "不禁"
}
],
"word": "不覺"
}
{
"head_templates": [
{
"args": {
"1": "vi",
"2": "adverb",
"3": "",
"4": "",
"head": "",
"tr": ""
},
"expansion": "不覺",
"name": "head"
},
{
"args": {
"sc": "Hani"
},
"expansion": "不覺",
"name": "vi-adv"
}
],
"lang": "Vietnamese",
"lang_code": "vi",
"pos": "adv",
"senses": [
{
"categories": [
"Vietnamese Chữ Hán",
"Vietnamese adverbs",
"Vietnamese adverbs in Han script",
"Vietnamese entries with incorrect language header",
"Vietnamese lemmas"
],
"glosses": [
"chữ Hán form of bất giác."
],
"links": [
[
"chữ Hán",
"chữ Hán#Vietnamese"
],
[
"bất giác",
"bất giác#Vietnamese"
]
]
}
],
"word": "不覺"
}
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-05-03 from the enwiktionary dump dated 2024-05-02 using wiktextract (f4fd8c9 and c9440ce). 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.