See သန်း in All languages combined, or Wiktionary
{
"derived": [
{
"_dis1": "0 0",
"roman": "hkresan:",
"word": "ခြေသန်း"
},
{
"_dis1": "0 0",
"roman": "nga:nu.san:",
"word": "ငါးနုသန်း"
},
{
"_dis1": "0 0",
"roman": "laksan:",
"word": "လက်သန်း"
},
{
"_dis1": "0 0",
"roman": "san:kre:ma.",
"word": "သန်းကြေးမ"
},
{
"_dis1": "0 0",
"roman": "san:tup",
"word": "သန်းတုပ်"
},
{
"_dis1": "0 0",
"roman": "san:hpya.",
"word": "သန်းဖျ"
}
],
"etymology_number": 1,
"etymology_templates": [
{
"args": {
"1": "my",
"2": "tbq-pro",
"3": "*s(y)ar",
"t": "louse"
},
"expansion": "Proto-Tibeto-Burman *s(y)ar (“louse”)",
"name": "inh"
},
{
"args": {
"1": "ahk",
"t": "idem",
"tr": "shɛ́-mɔ̀"
},
"expansion": "Akha [script needed] (shɛ́-mɔ̀, “idem”)",
"name": "cog"
}
],
"etymology_text": "From Proto-Tibeto-Burman *s(y)ar (“louse”). Cognate with Akha [script needed] (shɛ́-mɔ̀, “idem”) (STEDT).",
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-noun"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "noun",
"related": [
{
"_dis1": "0 0",
"roman": "htaukkram.",
"word": "ထောက်ကြံ့"
},
{
"_dis1": "0 0",
"roman": "hpanhka:",
"word": "ဖန်ခါး"
},
{
"_dis1": "0 0",
"english": "rum:",
"word": "ရုံး"
},
{
"_dis1": "0 0",
"roman": "lim",
"word": "လိမ်"
},
{
"_dis1": "0 0",
"roman": "sachcim.",
"word": "သစ်ဆိမ့်"
}
],
"senses": [
{
"glosses": [
"louse (insect of the order Psocodea)"
],
"id": "en-သန်း-my-noun-cqr15RyE",
"links": [
[
"louse",
"louse"
],
[
"Psocodea",
"Psocodea#Translingual"
]
]
},
{
"categories": [
{
"_dis": "14 8 15 6 28 27 1 1",
"kind": "other",
"name": "Burmese particles",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "13 7 18 4 24 26 4 4",
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 8 26 3 10 23 4 5",
"kind": "other",
"langcode": "my",
"name": "Combretum family plants",
"orig": "my:Combretum family plants",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "26 8 16 4 11 25 5 6",
"kind": "other",
"langcode": "my",
"name": "Trees",
"orig": "my:Trees",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"tree from the bark of which a dye is obtained; Terminalia oliveri"
],
"id": "en-သန်း-my-noun-Fx5s9mj5",
"links": [
[
"Daigakushorin",
"w:ja:大学書林"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"etymology_number": 2,
"etymology_templates": [
{
"args": {
"1": "och",
"2": "-"
},
"expansion": "Old Chinese",
"name": "cog"
},
{
"args": {
"1": "千",
"2": "thousand"
},
"expansion": "千 (OC *sn̥ʰiːn, “thousand”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
},
{
"form": "၁၀၀၀၀၀၀",
"tags": [
"digit"
]
}
],
"head_templates": [
{
"args": {
"1": "my",
"2": "numeral",
"3": "digit",
"4": "၁၀၀၀၀၀၀",
"cat2": "numbers"
},
"expansion": "သန်း • (san:) (digit ၁၀၀၀၀၀၀)",
"name": "head"
},
{
"args": {
"1": "၁၀၀၀၀၀၀"
},
"expansion": "သန်း • (san:) (digit ၁၀၀၀၀၀၀)",
"name": "my-num"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "num",
"senses": [
{
"glosses": [
"million"
],
"id": "en-သန်း-my-num-yM6WpboN",
"links": [
[
"million",
"million"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"etymology_number": 2,
"etymology_templates": [
{
"args": {
"1": "och",
"2": "-"
},
"expansion": "Old Chinese",
"name": "cog"
},
{
"args": {
"1": "千",
"2": "thousand"
},
"expansion": "千 (OC *sn̥ʰiːn, “thousand”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "my",
"2": "proper noun",
"head": "",
"sort": "",
"tr": ""
},
"expansion": "သန်း • (san:)",
"name": "head"
},
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-proper noun"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "name",
"senses": [
{
"categories": [
{
"kind": "other",
"name": "Burmese female given names",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Burmese given names",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Burmese male given names",
"parents": [],
"source": "w"
},
{
"kind": "other",
"name": "Burmese unisex given names",
"parents": [],
"source": "w"
},
{
"_dis": "14 8 15 6 28 27 1 1",
"kind": "other",
"name": "Burmese particles",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "13 7 18 4 24 26 4 4",
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 8 26 3 10 23 4 5",
"kind": "other",
"langcode": "my",
"name": "Combretum family plants",
"orig": "my:Combretum family plants",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "26 8 16 4 11 25 5 6",
"kind": "other",
"langcode": "my",
"name": "Trees",
"orig": "my:Trees",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "86 14",
"kind": "other",
"name": "Burmese numbers",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"a unisex given name"
],
"id": "en-သန်း-my-name-NHbuMNUu",
"links": [
[
"given name",
"given name"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"etymology_number": 3,
"etymology_templates": [
{
"args": {
"1": "zh",
"2": "-"
},
"expansion": "Chinese",
"name": "cog"
},
{
"args": {
"1": "闖",
"2": "to rush in, charge"
},
"expansion": "闖／闯 (chèn, “to rush in, charge”)",
"name": "zh-l"
},
{
"args": {
"1": "進",
"2": "to advance"
},
"expansion": "進 (OC *ʔslins, “to advance”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-particle"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "particle",
"senses": [
{
"categories": [
{
"_dis": "14 8 15 6 28 27 1 1",
"kind": "other",
"name": "Burmese particles",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "13 7 18 4 24 26 4 4",
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 8 26 3 10 23 4 5",
"kind": "other",
"langcode": "my",
"name": "Combretum family plants",
"orig": "my:Combretum family plants",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "26 8 16 4 11 25 5 6",
"kind": "other",
"langcode": "my",
"name": "Trees",
"orig": "my:Trees",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"particle suffixed to a verb to convey a sense of going or lying across (equivalent in usage to adverbs, 'across', 'athwart')"
],
"id": "en-သန်း-my-particle-ZvASGzB~"
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"derived": [
{
"_dis1": "0 0 0",
"roman": "ku:hkyanysan:hkyany",
"word": "ကူးချည်သန်းချည်"
},
{
"_dis1": "0 0 0",
"roman": "ku:san:",
"word": "ကူးသန်း"
},
{
"_dis1": "0 0 0",
"roman": "ku:san:raung:waire:",
"word": "ကူးသန်းရောင်းဝယ်ရေး"
},
{
"_dis1": "0 0 0",
"roman": "ca.ka:u:san:",
"word": "စကားဦးသန်း"
},
{
"_dis1": "0 0 0",
"roman": "citku:citsan:",
"word": "စိတ်ကူးစိတ်သန်း"
},
{
"_dis1": "0 0 0",
"roman": "htaung.san:na",
"word": "ထောင့်သန်းနာ"
},
{
"_dis1": "0 0 0",
"roman": "pyamsan:",
"word": "ပျံသန်း"
},
{
"_dis1": "0 0 0",
"roman": "hpratsan:",
"word": "ဖြတ်သန်း"
},
{
"_dis1": "0 0 0",
"roman": "hpran:san:",
"word": "ဖြန်းသန်း"
},
{
"_dis1": "0 0 0",
"roman": "hyaksan:",
"word": "ယှက်သန်း"
},
{
"_dis1": "0 0 0",
"roman": "ram:san:",
"word": "ရမ်းသန်း"
},
{
"_dis1": "0 0 0",
"roman": "san:hkaungsan:lwai:",
"word": "သန်းခေါင်သန်းလွဲ"
},
{
"_dis1": "0 0 0",
"roman": "a.ku:a.san:",
"word": "အကူးအသန်း"
},
{
"_dis1": "0 0 0",
"roman": "a.ripsan:",
"word": "အရိပ်သန်း"
}
],
"etymology_number": 3,
"etymology_templates": [
{
"args": {
"1": "zh",
"2": "-"
},
"expansion": "Chinese",
"name": "cog"
},
{
"args": {
"1": "闖",
"2": "to rush in, charge"
},
"expansion": "闖／闯 (chèn, “to rush in, charge”)",
"name": "zh-l"
},
{
"args": {
"1": "進",
"2": "to advance"
},
"expansion": "進 (OC *ʔslins, “to advance”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-verb"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "verb",
"senses": [
{
"categories": [
{
"_dis": "12 7 16 3 18 35 4 4",
"kind": "other",
"name": "Burmese entries with incorrect language header",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "14 8 15 6 28 27 1 1",
"kind": "other",
"name": "Burmese particles",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "13 7 18 4 24 26 4 4",
"kind": "other",
"name": "Pages with 2 entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "10 6 18 3 20 37 3 3",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 8 26 3 10 23 4 5",
"kind": "other",
"langcode": "my",
"name": "Combretum family plants",
"orig": "my:Combretum family plants",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "15 16 14 1 16 36 0 2",
"kind": "other",
"langcode": "my",
"name": "Insects",
"orig": "my:Insects",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "26 8 16 4 11 25 5 6",
"kind": "other",
"langcode": "my",
"name": "Trees",
"orig": "my:Trees",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"to cross over; hover over; brush by"
],
"id": "en-သန်း-my-verb-i3e~xV7b",
"links": [
[
"cross over",
"cross over"
],
[
"hover",
"hover"
],
[
"over",
"over"
],
[
"brush by",
"brush by"
]
]
},
{
"glosses": [
"to be tinted with"
],
"id": "en-သန်း-my-verb-ql2-1Nhx",
"links": [
[
"be",
"be"
],
[
"tinted",
"tinted"
],
[
"with",
"with"
]
]
},
{
"glosses": [
"to flush (with anger); have a hint of (a smile)"
],
"id": "en-သန်း-my-verb-ucM2sLWu",
"links": [
[
"flush",
"flush"
],
[
"anger",
"anger"
],
[
"have",
"have"
],
[
"hint",
"hint"
],
[
"smile",
"smile"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"categories": [
"Burmese entries with incorrect language header",
"Burmese lemmas",
"Burmese nouns",
"Burmese particles",
"Burmese terms derived from Proto-Tibeto-Burman",
"Burmese terms inherited from Proto-Tibeto-Burman",
"Burmese terms with IPA pronunciation",
"Burmese verbs",
"Pages with 2 entries",
"Pages with entries",
"Requests for native script for Akha terms",
"my:Combretum family plants",
"my:Insects",
"my:Trees"
],
"derived": [
{
"roman": "hkresan:",
"word": "ခြေသန်း"
},
{
"roman": "nga:nu.san:",
"word": "ငါးနုသန်း"
},
{
"roman": "laksan:",
"word": "လက်သန်း"
},
{
"roman": "san:kre:ma.",
"word": "သန်းကြေးမ"
},
{
"roman": "san:tup",
"word": "သန်းတုပ်"
},
{
"roman": "san:hpya.",
"word": "သန်းဖျ"
}
],
"etymology_number": 1,
"etymology_templates": [
{
"args": {
"1": "my",
"2": "tbq-pro",
"3": "*s(y)ar",
"t": "louse"
},
"expansion": "Proto-Tibeto-Burman *s(y)ar (“louse”)",
"name": "inh"
},
{
"args": {
"1": "ahk",
"t": "idem",
"tr": "shɛ́-mɔ̀"
},
"expansion": "Akha [script needed] (shɛ́-mɔ̀, “idem”)",
"name": "cog"
}
],
"etymology_text": "From Proto-Tibeto-Burman *s(y)ar (“louse”). Cognate with Akha [script needed] (shɛ́-mɔ̀, “idem”) (STEDT).",
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-noun"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "noun",
"related": [
{
"roman": "htaukkram.",
"word": "ထောက်ကြံ့"
},
{
"roman": "hpanhka:",
"word": "ဖန်ခါး"
},
{
"english": "rum:",
"word": "ရုံး"
},
{
"roman": "lim",
"word": "လိမ်"
},
{
"roman": "sachcim.",
"word": "သစ်ဆိမ့်"
}
],
"senses": [
{
"glosses": [
"louse (insect of the order Psocodea)"
],
"links": [
[
"louse",
"louse"
],
[
"Psocodea",
"Psocodea#Translingual"
]
]
},
{
"categories": [
"Entries using missing taxonomic name (species)"
],
"glosses": [
"tree from the bark of which a dye is obtained; Terminalia oliveri"
],
"links": [
[
"Daigakushorin",
"w:ja:大学書林"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"categories": [
"Burmese entries with incorrect language header",
"Burmese lemmas",
"Burmese numbers",
"Burmese numerals",
"Burmese particles",
"Burmese proper nouns",
"Burmese terms with IPA pronunciation",
"Burmese verbs",
"Pages with 2 entries",
"Pages with entries",
"my:Combretum family plants",
"my:Insects",
"my:Trees"
],
"etymology_number": 2,
"etymology_templates": [
{
"args": {
"1": "och",
"2": "-"
},
"expansion": "Old Chinese",
"name": "cog"
},
{
"args": {
"1": "千",
"2": "thousand"
},
"expansion": "千 (OC *sn̥ʰiːn, “thousand”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
},
{
"form": "၁၀၀၀၀၀၀",
"tags": [
"digit"
]
}
],
"head_templates": [
{
"args": {
"1": "my",
"2": "numeral",
"3": "digit",
"4": "၁၀၀၀၀၀၀",
"cat2": "numbers"
},
"expansion": "သန်း • (san:) (digit ၁၀၀၀၀၀၀)",
"name": "head"
},
{
"args": {
"1": "၁၀၀၀၀၀၀"
},
"expansion": "သန်း • (san:) (digit ၁၀၀၀၀၀၀)",
"name": "my-num"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "num",
"senses": [
{
"glosses": [
"million"
],
"links": [
[
"million",
"million"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"categories": [
"Burmese entries with incorrect language header",
"Burmese lemmas",
"Burmese numbers",
"Burmese numerals",
"Burmese particles",
"Burmese proper nouns",
"Burmese terms with IPA pronunciation",
"Burmese verbs",
"Pages with 2 entries",
"Pages with entries",
"my:Combretum family plants",
"my:Insects",
"my:Trees"
],
"etymology_number": 2,
"etymology_templates": [
{
"args": {
"1": "och",
"2": "-"
},
"expansion": "Old Chinese",
"name": "cog"
},
{
"args": {
"1": "千",
"2": "thousand"
},
"expansion": "千 (OC *sn̥ʰiːn, “thousand”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {
"1": "my",
"2": "proper noun",
"head": "",
"sort": "",
"tr": ""
},
"expansion": "သန်း • (san:)",
"name": "head"
},
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-proper noun"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "name",
"senses": [
{
"categories": [
"Burmese female given names",
"Burmese given names",
"Burmese male given names",
"Burmese unisex given names"
],
"glosses": [
"a unisex given name"
],
"links": [
[
"given name",
"given name"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"categories": [
"Burmese entries with incorrect language header",
"Burmese lemmas",
"Burmese particles",
"Burmese terms with IPA pronunciation",
"Burmese verbs",
"Pages with 2 entries",
"Pages with entries",
"my:Combretum family plants",
"my:Insects",
"my:Trees"
],
"etymology_number": 3,
"etymology_templates": [
{
"args": {
"1": "zh",
"2": "-"
},
"expansion": "Chinese",
"name": "cog"
},
{
"args": {
"1": "闖",
"2": "to rush in, charge"
},
"expansion": "闖／闯 (chèn, “to rush in, charge”)",
"name": "zh-l"
},
{
"args": {
"1": "進",
"2": "to advance"
},
"expansion": "進 (OC *ʔslins, “to advance”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-particle"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "particle",
"senses": [
{
"glosses": [
"particle suffixed to a verb to convey a sense of going or lying across (equivalent in usage to adverbs, 'across', 'athwart')"
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
{
"categories": [
"Burmese entries with incorrect language header",
"Burmese lemmas",
"Burmese particles",
"Burmese terms with IPA pronunciation",
"Burmese verbs",
"Pages with 2 entries",
"Pages with entries",
"my:Combretum family plants",
"my:Insects",
"my:Trees"
],
"derived": [
{
"roman": "ku:hkyanysan:hkyany",
"word": "ကူးချည်သန်းချည်"
},
{
"roman": "ku:san:",
"word": "ကူးသန်း"
},
{
"roman": "ku:san:raung:waire:",
"word": "ကူးသန်းရောင်းဝယ်ရေး"
},
{
"roman": "ca.ka:u:san:",
"word": "စကားဦးသန်း"
},
{
"roman": "citku:citsan:",
"word": "စိတ်ကူးစိတ်သန်း"
},
{
"roman": "htaung.san:na",
"word": "ထောင့်သန်းနာ"
},
{
"roman": "pyamsan:",
"word": "ပျံသန်း"
},
{
"roman": "hpratsan:",
"word": "ဖြတ်သန်း"
},
{
"roman": "hpran:san:",
"word": "ဖြန်းသန်း"
},
{
"roman": "hyaksan:",
"word": "ယှက်သန်း"
},
{
"roman": "ram:san:",
"word": "ရမ်းသန်း"
},
{
"roman": "san:hkaungsan:lwai:",
"word": "သန်းခေါင်သန်းလွဲ"
},
{
"roman": "a.ku:a.san:",
"word": "အကူးအသန်း"
},
{
"roman": "a.ripsan:",
"word": "အရိပ်သန်း"
}
],
"etymology_number": 3,
"etymology_templates": [
{
"args": {
"1": "zh",
"2": "-"
},
"expansion": "Chinese",
"name": "cog"
},
{
"args": {
"1": "闖",
"2": "to rush in, charge"
},
"expansion": "闖／闯 (chèn, “to rush in, charge”)",
"name": "zh-l"
},
{
"args": {
"1": "進",
"2": "to advance"
},
"expansion": "進 (OC *ʔslins, “to advance”)",
"name": "och-l"
}
],
"forms": [
{
"form": "san:",
"tags": [
"romanization"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "သန်း • (san:)",
"name": "my-verb"
}
],
"lang": "Burmese",
"lang_code": "my",
"pos": "verb",
"senses": [
{
"glosses": [
"to cross over; hover over; brush by"
],
"links": [
[
"cross over",
"cross over"
],
[
"hover",
"hover"
],
[
"over",
"over"
],
[
"brush by",
"brush by"
]
]
},
{
"glosses": [
"to be tinted with"
],
"links": [
[
"be",
"be"
],
[
"tinted",
"tinted"
],
[
"with",
"with"
]
]
},
{
"glosses": [
"to flush (with anger); have a hint of (a smile)"
],
"links": [
[
"flush",
"flush"
],
[
"anger",
"anger"
],
[
"have",
"have"
],
[
"hint",
"hint"
],
[
"smile",
"smile"
]
]
}
],
"sounds": [
{
"ipa": "/θáɴ/"
}
],
"word": "သန်း"
}
Download raw JSONL data for သန်း meaning in Burmese (7.7kB)
This page is a part of the kaikki.org machine-readable Burmese dictionary. This dictionary is based on structured data extracted on 2025-06-10 from the enwiktionary dump dated 2025-06-01 using wiktextract (58c391d 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.