See তেজ on Wiktionary
{ "etymology_templates": [ { "args": { "1": "as", "2": "inc-oas", "3": "তেজ" }, "expansion": "Early Assamese তেজ (tejo)", "name": "der" }, { "args": { "1": "as", "2": "sa", "3": "तेजोज" }, "expansion": "Sanskrit तेजोज (tejoja)", "name": "der" } ], "etymology_text": "From Early Assamese তেজ (tejo), from Sanskrit तेजोज (tejoja) or त्वग्ज (tvagja). Compare তেজা (teza, “to sacrifice, to give up”).", "forms": [ { "form": "tez", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "as-noun2-oখিনি", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "তেজ", "roman": "tez", "source": "declension", "tags": [ "absolutive", "indefinite" ] }, { "form": "তেজখিনি", "roman": "tezkhini", "source": "declension", "tags": [ "absolutive", "definite", "specific" ] }, { "form": "তেজবোৰ", "roman": "tezbür", "source": "declension", "tags": [ "absolutive", "definite", "unspecified" ] }, { "form": "তেজবিলাক", "roman": "tezbilak", "source": "declension", "tags": [ "absolutive", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহ", "roman": "tezxomuh", "source": "declension", "tags": [ "absolutive", "deferential", "definite", "unspecified" ] }, { "form": "তেজে", "roman": "teze", "source": "declension", "tags": [ "ergative", "indefinite" ] }, { "form": "তেজখিনিয়ে", "roman": "tezkhinie", "source": "declension", "tags": [ "definite", "ergative", "specific" ] }, { "form": "তেজবোৰে", "roman": "tezbüre", "source": "declension", "tags": [ "definite", "ergative", "unspecified" ] }, { "form": "তেজবিলাকে", "roman": "tezbilake", "source": "declension", "tags": [ "definite", "ergative", "formal", "unspecified" ] }, { "form": "তেজসমূহে", "roman": "tezxomuhe", "source": "declension", "tags": [ "deferential", "definite", "ergative", "unspecified" ] }, { "form": "তেজক", "roman": "tezok", "source": "declension", "tags": [ "accusative", "indefinite" ] }, { "form": "তেজখিনিক", "roman": "tezkhinik", "source": "declension", "tags": [ "accusative", "definite", "specific" ] }, { "form": "তেজবোৰক", "roman": "tezbürok", "source": "declension", "tags": [ "accusative", "definite", "unspecified" ] }, { "form": "তেজবিলাকক", "roman": "tezbilakok", "source": "declension", "tags": [ "accusative", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহক", "roman": "tezxomuhok", "source": "declension", "tags": [ "accusative", "deferential", "definite", "unspecified" ] }, { "form": "তেজৰ", "roman": "tezor", "source": "declension", "tags": [ "genitive", "indefinite" ] }, { "form": "তেজখিনিৰ", "roman": "tezkhinir", "source": "declension", "tags": [ "definite", "genitive", "specific" ] }, { "form": "তেজবোৰৰ", "roman": "tezbüror", "source": "declension", "tags": [ "definite", "genitive", "unspecified" ] }, { "form": "তেজবিলাকৰ", "roman": "tezbilakor", "source": "declension", "tags": [ "definite", "formal", "genitive", "unspecified" ] }, { "form": "তেজসমূহৰ", "roman": "tezxomuhor", "source": "declension", "tags": [ "deferential", "definite", "genitive", "unspecified" ] }, { "form": "তেজলৈ", "roman": "tezoloi", "source": "declension", "tags": [ "dative", "indefinite" ] }, { "form": "তেজখিনিলৈ", "roman": "tezkhiniloi", "source": "declension", "tags": [ "dative", "definite", "specific" ] }, { "form": "তেজবোৰলৈ", "roman": "tezbüroloi", "source": "declension", "tags": [ "dative", "definite", "unspecified" ] }, { "form": "তেজবিলাকলৈ", "roman": "tezbilakoloi", "source": "declension", "tags": [ "dative", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহলৈ", "roman": "tezxomuholoi", "source": "declension", "tags": [ "dative", "deferential", "definite", "unspecified" ] }, { "form": "তেজেৰে", "roman": "tezere", "source": "declension", "tags": [ "indefinite", "instrumental" ] }, { "form": "তেজখিনিৰে", "roman": "tezkhinire", "source": "declension", "tags": [ "definite", "instrumental", "specific" ] }, { "form": "তেজবোৰেৰে", "roman": "tezbürere", "source": "declension", "tags": [ "definite", "instrumental", "unspecified" ] }, { "form": "তেজবিলাকেৰে", "roman": "tezbilakere", "source": "declension", "tags": [ "definite", "formal", "instrumental", "unspecified" ] }, { "form": "তেজসমূহেৰে", "roman": "tezxomuhere", "source": "declension", "tags": [ "deferential", "definite", "instrumental", "unspecified" ] }, { "form": "তেজত", "roman": "tezot", "source": "declension", "tags": [ "indefinite", "locative" ] }, { "form": "তেজখিনিত", "roman": "tezkhinit", "source": "declension", "tags": [ "definite", "locative", "specific" ] }, { "form": "তেজবোৰত", "roman": "tezbürot", "source": "declension", "tags": [ "definite", "locative", "unspecified" ] }, { "form": "তেজবিলাকত", "roman": "tezbilakot", "source": "declension", "tags": [ "definite", "formal", "locative", "unspecified" ] }, { "form": "তেজসমূহত", "roman": "tezxomuhot", "source": "declension", "tags": [ "deferential", "definite", "locative", "unspecified" ] } ], "head_templates": [ { "args": { "1": "as", "2": "noun" }, "expansion": "তেজ • (tez)", "name": "head" } ], "lang": "Assamese", "lang_code": "as", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Assamese entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "48 48 2 2", "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w+disamb" }, { "_dis": "48 48 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "blood" ], "id": "en-তেজ-as-noun-Po5AwK9f", "links": [ [ "blood", "blood" ] ] } ], "word": "তেজ" } { "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "as", "2": "তেজ" }, "expansion": "Assamese: তেজ (tez)", "name": "desc" } ], "text": "Assamese: তেজ (tez)" } ], "etymology_templates": [ { "args": { "1": "inc-oas", "2": "sa", "3": "तेजोज" }, "expansion": "Sanskrit तेजोज (tejoja)", "name": "der" } ], "etymology_text": "From Sanskrit तेजोज (tejoja) or त्वग्ज (tvagja).", "forms": [ { "form": "tejo", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "1": "inc-oas", "2": "noun" }, "expansion": "তেজ (tejo)", "name": "head" } ], "lang": "Early Assamese", "lang_code": "inc-oas", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Early Assamese entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "48 48 2 2", "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w+disamb" }, { "_dis": "48 48 2 2", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "examples": [ { "english": "The river flows with the blood of monkeys and bears", "roman": "banororo bhalukoro teje bohe gaṅgo,", "text": "বানৰৰ ভালুকৰ তেজে বহে গাঙ্গ।", "type": "example" } ], "glosses": [ "blood" ], "id": "en-তেজ-inc-oas-noun-Po5AwK9f", "links": [ [ "blood", "blood" ] ] } ], "word": "তেজ" } { "head_templates": [ { "args": { "1": "n" }, "expansion": "তেজ n", "name": "pi-noun" } ], "lang": "Pali", "lang_code": "pi", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Bengali script", "parents": [], "source": "w" }, { "_dis": "50 50", "kind": "other", "name": "Pali entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "form_of": [ { "extra": "brilliance", "word": "teja" } ], "glosses": [ "Bengali script form of teja (“brilliance”)" ], "id": "en-তেজ-pi-noun-q4lKq-BL", "links": [ [ "teja", "teja#Pali" ] ], "tags": [ "Bengali", "form-of", "neuter" ] } ], "word": "তেজ" } { "head_templates": [ { "args": { "1": "pi", "2": "noun form", "tr": "-" }, "expansion": "তেজ", "name": "head" } ], "lang": "Pali", "lang_code": "pi", "pos": "noun", "senses": [ { "categories": [ { "kind": "other", "name": "Bengali script", "parents": [], "source": "w" }, { "kind": "other", "name": "Inflections with a red link for lemma", "parents": [], "source": "w" }, { "_dis": "50 50", "kind": "other", "name": "Pali entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "form_of": [ { "extra": "tejas, “brilliance”", "word": "teja" }, { "extra": "tejas, “brilliance”", "word": "which is vocative singular of তেজস্" } ], "glosses": [ "Bengali script form of teja, which is vocative singular of তেজস্ (tejas, “brilliance”)" ], "id": "en-তেজ-pi-noun-BSoqtL8M", "links": [ [ "teja", "teja#Pali" ], [ "তেজস্", "তেজস্#Pali" ], [ "tejas", "tejas#Pali" ] ], "synonyms": [ { "_dis1": "0 100", "tags": [ "Latin", "character" ], "word": "teja" }, { "_dis1": "0 100", "tags": [ "Brahmi", "character" ], "word": "𑀢" }, { "_dis1": "0 100", "tags": [ "Brahmi", "character" ], "word": "𑁂" }, { "_dis1": "0 100", "tags": [ "Brahmi", "character" ], "word": "𑀚" }, { "_dis1": "0 100", "tags": [ "Devanagari", "character" ], "word": "त" }, { "_dis1": "0 100", "tags": [ "Devanagari", "character" ], "word": "े" }, { "_dis1": "0 100", "tags": [ "Devanagari", "character" ], "word": "ज" }, { "_dis1": "0 100", "tags": [ "Sinhalese", "character" ], "word": "තෙජ" }, { "_dis1": "0 100", "word": "တေဇ" }, { "_dis1": "0 100", "tags": [ "Burmese", "character" ], "word": "တေၹ" }, { "_dis1": "0 100", "word": "เตช" }, { "_dis1": "0 100", "tags": [ "Thai", "character" ], "word": "เตชะ" }, { "_dis1": "0 100", "tags": [ "Tai-Tham", "character" ], "word": "ᨲᩮᨩ" }, { "_dis1": "0 100", "word": "ເຕຊ" }, { "_dis1": "0 100", "tags": [ "Lao", "character" ], "word": "ເຕຊະ" }, { "_dis1": "0 100", "tags": [ "Khmer", "character" ], "word": "តេជ" }, { "_dis1": "0 100", "tags": [ "Chakma", "character" ], "word": "𑄖𑄬𑄎" } ], "tags": [ "Bengali", "form-of" ] } ], "word": "তেজ" }
{ "categories": [ "Pages with 3 entries", "Pages with entries" ], "etymology_templates": [ { "args": { "1": "as", "2": "inc-oas", "3": "তেজ" }, "expansion": "Early Assamese তেজ (tejo)", "name": "der" }, { "args": { "1": "as", "2": "sa", "3": "तेजोज" }, "expansion": "Sanskrit तेजोज (tejoja)", "name": "der" } ], "etymology_text": "From Early Assamese তেজ (tejo), from Sanskrit तेजोज (tejoja) or त्वग्ज (tvagja). Compare তেজা (teza, “to sacrifice, to give up”).", "forms": [ { "form": "tez", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "as-noun2-oখিনি", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "তেজ", "roman": "tez", "source": "declension", "tags": [ "absolutive", "indefinite" ] }, { "form": "তেজখিনি", "roman": "tezkhini", "source": "declension", "tags": [ "absolutive", "definite", "specific" ] }, { "form": "তেজবোৰ", "roman": "tezbür", "source": "declension", "tags": [ "absolutive", "definite", "unspecified" ] }, { "form": "তেজবিলাক", "roman": "tezbilak", "source": "declension", "tags": [ "absolutive", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহ", "roman": "tezxomuh", "source": "declension", "tags": [ "absolutive", "deferential", "definite", "unspecified" ] }, { "form": "তেজে", "roman": "teze", "source": "declension", "tags": [ "ergative", "indefinite" ] }, { "form": "তেজখিনিয়ে", "roman": "tezkhinie", "source": "declension", "tags": [ "definite", "ergative", "specific" ] }, { "form": "তেজবোৰে", "roman": "tezbüre", "source": "declension", "tags": [ "definite", "ergative", "unspecified" ] }, { "form": "তেজবিলাকে", "roman": "tezbilake", "source": "declension", "tags": [ "definite", "ergative", "formal", "unspecified" ] }, { "form": "তেজসমূহে", "roman": "tezxomuhe", "source": "declension", "tags": [ "deferential", "definite", "ergative", "unspecified" ] }, { "form": "তেজক", "roman": "tezok", "source": "declension", "tags": [ "accusative", "indefinite" ] }, { "form": "তেজখিনিক", "roman": "tezkhinik", "source": "declension", "tags": [ "accusative", "definite", "specific" ] }, { "form": "তেজবোৰক", "roman": "tezbürok", "source": "declension", "tags": [ "accusative", "definite", "unspecified" ] }, { "form": "তেজবিলাকক", "roman": "tezbilakok", "source": "declension", "tags": [ "accusative", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহক", "roman": "tezxomuhok", "source": "declension", "tags": [ "accusative", "deferential", "definite", "unspecified" ] }, { "form": "তেজৰ", "roman": "tezor", "source": "declension", "tags": [ "genitive", "indefinite" ] }, { "form": "তেজখিনিৰ", "roman": "tezkhinir", "source": "declension", "tags": [ "definite", "genitive", "specific" ] }, { "form": "তেজবোৰৰ", "roman": "tezbüror", "source": "declension", "tags": [ "definite", "genitive", "unspecified" ] }, { "form": "তেজবিলাকৰ", "roman": "tezbilakor", "source": "declension", "tags": [ "definite", "formal", "genitive", "unspecified" ] }, { "form": "তেজসমূহৰ", "roman": "tezxomuhor", "source": "declension", "tags": [ "deferential", "definite", "genitive", "unspecified" ] }, { "form": "তেজলৈ", "roman": "tezoloi", "source": "declension", "tags": [ "dative", "indefinite" ] }, { "form": "তেজখিনিলৈ", "roman": "tezkhiniloi", "source": "declension", "tags": [ "dative", "definite", "specific" ] }, { "form": "তেজবোৰলৈ", "roman": "tezbüroloi", "source": "declension", "tags": [ "dative", "definite", "unspecified" ] }, { "form": "তেজবিলাকলৈ", "roman": "tezbilakoloi", "source": "declension", "tags": [ "dative", "definite", "formal", "unspecified" ] }, { "form": "তেজসমূহলৈ", "roman": "tezxomuholoi", "source": "declension", "tags": [ "dative", "deferential", "definite", "unspecified" ] }, { "form": "তেজেৰে", "roman": "tezere", "source": "declension", "tags": [ "indefinite", "instrumental" ] }, { "form": "তেজখিনিৰে", "roman": "tezkhinire", "source": "declension", "tags": [ "definite", "instrumental", "specific" ] }, { "form": "তেজবোৰেৰে", "roman": "tezbürere", "source": "declension", "tags": [ "definite", "instrumental", "unspecified" ] }, { "form": "তেজবিলাকেৰে", "roman": "tezbilakere", "source": "declension", "tags": [ "definite", "formal", "instrumental", "unspecified" ] }, { "form": "তেজসমূহেৰে", "roman": "tezxomuhere", "source": "declension", "tags": [ "deferential", "definite", "instrumental", "unspecified" ] }, { "form": "তেজত", "roman": "tezot", "source": "declension", "tags": [ "indefinite", "locative" ] }, { "form": "তেজখিনিত", "roman": "tezkhinit", "source": "declension", "tags": [ "definite", "locative", "specific" ] }, { "form": "তেজবোৰত", "roman": "tezbürot", "source": "declension", "tags": [ "definite", "locative", "unspecified" ] }, { "form": "তেজবিলাকত", "roman": "tezbilakot", "source": "declension", "tags": [ "definite", "formal", "locative", "unspecified" ] }, { "form": "তেজসমূহত", "roman": "tezxomuhot", "source": "declension", "tags": [ "deferential", "definite", "locative", "unspecified" ] } ], "head_templates": [ { "args": { "1": "as", "2": "noun" }, "expansion": "তেজ • (tez)", "name": "head" } ], "lang": "Assamese", "lang_code": "as", "pos": "noun", "senses": [ { "categories": [ "Assamese entries with incorrect language header", "Assamese lemmas", "Assamese nouns", "Assamese terms derived from Early Assamese", "Assamese terms derived from Sanskrit", "Pages with 3 entries", "Pages with entries" ], "glosses": [ "blood" ], "links": [ [ "blood", "blood" ] ] } ], "word": "তেজ" } { "categories": [ "Pages with 3 entries", "Pages with entries" ], "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "as", "2": "তেজ" }, "expansion": "Assamese: তেজ (tez)", "name": "desc" } ], "text": "Assamese: তেজ (tez)" } ], "etymology_templates": [ { "args": { "1": "inc-oas", "2": "sa", "3": "तेजोज" }, "expansion": "Sanskrit तेजोज (tejoja)", "name": "der" } ], "etymology_text": "From Sanskrit तेजोज (tejoja) or त्वग्ज (tvagja).", "forms": [ { "form": "tejo", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "1": "inc-oas", "2": "noun" }, "expansion": "তেজ (tejo)", "name": "head" } ], "lang": "Early Assamese", "lang_code": "inc-oas", "pos": "noun", "senses": [ { "categories": [ "Early Assamese entries with incorrect language header", "Early Assamese lemmas", "Early Assamese nouns", "Early Assamese terms derived from Sanskrit", "Early Assamese terms with usage examples", "Pages with 3 entries", "Pages with entries" ], "examples": [ { "english": "The river flows with the blood of monkeys and bears", "roman": "banororo bhalukoro teje bohe gaṅgo,", "text": "বানৰৰ ভালুকৰ তেজে বহে গাঙ্গ।", "type": "example" } ], "glosses": [ "blood" ], "links": [ [ "blood", "blood" ] ] } ], "word": "তেজ" } { "categories": [ "Pages with 3 entries", "Pages with entries", "Pali entries with incorrect language header", "Pali lemmas", "Pali neuter nouns", "Pali non-lemma forms", "Pali noun forms", "Pali nouns", "Pali nouns in Bengali script" ], "head_templates": [ { "args": { "1": "n" }, "expansion": "তেজ n", "name": "pi-noun" } ], "lang": "Pali", "lang_code": "pi", "pos": "noun", "senses": [ { "categories": [ "Bengali script" ], "form_of": [ { "extra": "brilliance", "word": "teja" } ], "glosses": [ "Bengali script form of teja (“brilliance”)" ], "links": [ [ "teja", "teja#Pali" ] ], "tags": [ "Bengali", "form-of", "neuter" ] } ], "synonyms": [ { "tags": [ "Latin", "character" ], "word": "teja" }, { "tags": [ "Brahmi", "character" ], "word": "𑀢" }, { "tags": [ "Brahmi", "character" ], "word": "𑁂" }, { "tags": [ "Brahmi", "character" ], "word": "𑀚" }, { "tags": [ "Devanagari", "character" ], "word": "त" }, { "tags": [ "Devanagari", "character" ], "word": "े" }, { "tags": [ "Devanagari", "character" ], "word": "ज" }, { "tags": [ "Sinhalese", "character" ], "word": "තෙජ" }, { "word": "တေဇ" }, { "tags": [ "Burmese", "character" ], "word": "တေၹ" }, { "word": "เตช" }, { "tags": [ "Thai", "character" ], "word": "เตชะ" }, { "tags": [ "Tai-Tham", "character" ], "word": "ᨲᩮᨩ" }, { "word": "ເຕຊ" }, { "tags": [ "Lao", "character" ], "word": "ເຕຊະ" }, { "tags": [ "Khmer", "character" ], "word": "តេជ" }, { "tags": [ "Chakma", "character" ], "word": "𑄖𑄬𑄎" } ], "word": "তেজ" } { "categories": [ "Pages with 3 entries", "Pages with entries", "Pali entries with incorrect language header", "Pali lemmas", "Pali neuter nouns", "Pali non-lemma forms", "Pali noun forms", "Pali nouns", "Pali nouns in Bengali script" ], "head_templates": [ { "args": { "1": "pi", "2": "noun form", "tr": "-" }, "expansion": "তেজ", "name": "head" } ], "lang": "Pali", "lang_code": "pi", "pos": "noun", "senses": [ { "categories": [ "Bengali script", "Inflections with a red link for lemma" ], "form_of": [ { "extra": "tejas, “brilliance”", "word": "teja" }, { "extra": "tejas, “brilliance”", "word": "which is vocative singular of তেজস্" } ], "glosses": [ "Bengali script form of teja, which is vocative singular of তেজস্ (tejas, “brilliance”)" ], "links": [ [ "teja", "teja#Pali" ], [ "তেজস্", "তেজস্#Pali" ], [ "tejas", "tejas#Pali" ] ], "tags": [ "Bengali", "form-of" ] } ], "synonyms": [ { "tags": [ "Latin", "character" ], "word": "teja" }, { "tags": [ "Brahmi", "character" ], "word": "𑀢" }, { "tags": [ "Brahmi", "character" ], "word": "𑁂" }, { "tags": [ "Brahmi", "character" ], "word": "𑀚" }, { "tags": [ "Devanagari", "character" ], "word": "त" }, { "tags": [ "Devanagari", "character" ], "word": "े" }, { "tags": [ "Devanagari", "character" ], "word": "ज" }, { "tags": [ "Sinhalese", "character" ], "word": "තෙජ" }, { "word": "တေဇ" }, { "tags": [ "Burmese", "character" ], "word": "တေၹ" }, { "word": "เตช" }, { "tags": [ "Thai", "character" ], "word": "เตชะ" }, { "tags": [ "Tai-Tham", "character" ], "word": "ᨲᩮᨩ" }, { "word": "ເຕຊ" }, { "tags": [ "Lao", "character" ], "word": "ເຕຊະ" }, { "tags": [ "Khmer", "character" ], "word": "តេជ" }, { "tags": [ "Chakma", "character" ], "word": "𑄖𑄬𑄎" } ], "word": "তেজ" }
Download raw JSONL data for তেজ meaning in All languages combined (10.2kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-11-06 from the enwiktionary dump dated 2024-10-02 using wiktextract (fbeafe8 and 7f03c9b). 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.