See सरोज on Wiktionary
{ "etymology_templates": [ { "args": { "1": "hi", "2": "sa", "3": "सरोज" }, "expansion": "Learned borrowing from Sanskrit सरोज (saroja)", "name": "lbor" } ], "etymology_text": "Learned borrowing from Sanskrit सरोज (saroja).", "forms": [ { "form": "saroj", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "hi-ndecl", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "cons-stem", "source": "declension", "tags": [ "class" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "direct", "singular" ] }, { "form": "सरोजें", "roman": "sarojẽ", "source": "declension", "tags": [ "direct", "plural" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "oblique", "singular" ] }, { "form": "सरोजों", "roman": "sarojõ", "source": "declension", "tags": [ "oblique", "plural" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "singular", "vocative" ] }, { "form": "सरोजो", "roman": "sarojo", "source": "declension", "tags": [ "plural", "vocative" ] } ], "head_templates": [ { "args": { "g": "f" }, "expansion": "सरोज • (saroj) f", "name": "hi-proper noun" } ], "inflection_templates": [ { "args": { "1": "<F>" }, "name": "hi-ndecl" } ], "lang": "Hindi", "lang_code": "hi", "pos": "name", "senses": [ { "categories": [ { "kind": "other", "name": "Hindi entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "topical", "name": "Hindi female given names", "parents": [ "Female given names", "Given names", "Names", "All topics", "Proper nouns", "Terms by semantic function", "Fundamental", "Nouns", "Lemmas" ], "source": "w" }, { "kind": "topical", "name": "Hindi given names", "parents": [ "Given names", "Names", "All topics", "Proper nouns", "Terms by semantic function", "Fundamental", "Nouns", "Lemmas" ], "source": "w" }, { "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "38 45 11 0 6", "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w+disamb" }, { "_dis": "35 41 15 0 7", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "a female given name, Saroj, from Sanskrit" ], "id": "en-सरोज-hi-name-kz8pLG3v", "links": [ [ "given name", "given name" ], [ "Saroj", "Saroj#English" ] ] } ], "sounds": [ { "ipa": "/sə.ɾoːd͡ʒ/", "tags": [ "Delhi" ] }, { "ipa": "[sɐ.ɾoːd͡ʒ]", "tags": [ "Delhi" ] } ], "word": "सरोज" } { "forms": [ { "form": "saroj", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "ne-decl-noun-sg", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "सरोज [sʌɾoz]", "source": "declension", "tags": [ "nominative", "singular" ] }, { "form": "सरोज [sʌɾodz]", "source": "declension", "tags": [ "nominative", "singular" ] }, { "form": "सरोजलाई [sʌɾozläi]", "source": "declension", "tags": [ "accusative", "singular" ] }, { "form": "सरोजलाई [sʌɾodzläi]", "source": "declension", "tags": [ "accusative", "singular" ] }, { "form": "instrumental", "source": "declension", "tags": [ "accusative" ] }, { "form": "ergative", "source": "declension", "tags": [ "accusative" ] }, { "form": "सरोजले [sʌɾozle]", "source": "declension", "tags": [ "singular" ] }, { "form": "सरोजले [sʌɾodzle]", "source": "declension", "tags": [ "singular" ] }, { "form": "सरोजलाई [sʌɾozläi]", "source": "declension", "tags": [ "dative", "singular" ] }, { "form": "सरोजलाई [sʌɾodzläi]", "source": "declension", "tags": [ "dative", "singular" ] }, { "form": "सरोजबाट [sʌɾozbäʈʌ]", "source": "declension", "tags": [ "ablative", "singular" ] }, { "form": "सरोजबाट [sʌɾodzbäʈʌ]", "source": "declension", "tags": [ "ablative", "singular" ] }, { "form": "सरोजको [sʌɾozko]", "source": "declension", "tags": [ "genitive", "singular" ] }, { "form": "सरोजको [sʌɾodzko]", "source": "declension", "tags": [ "genitive", "singular" ] }, { "form": "सरोजमा [sʌɾozmä]", "source": "declension", "tags": [ "locative", "singular" ] }, { "form": "सरोजमा [sʌɾodzmä]", "source": "declension", "tags": [ "locative", "singular" ] } ], "head_templates": [ { "args": {}, "expansion": "सरोज • (saroj)", "name": "ne-proper noun" } ], "inflection_templates": [ { "args": {}, "name": "ne-decl-noun-sg" } ], "lang": "Nepali", "lang_code": "ne", "pos": "name", "senses": [ { "categories": [ { "kind": "other", "name": "Nepali entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w" }, { "kind": "topical", "name": "Nepali given names", "parents": [ "Given names", "Names", "All topics", "Proper nouns", "Terms by semantic function", "Fundamental", "Nouns", "Lemmas" ], "source": "w" }, { "kind": "topical", "name": "Nepali male given names", "parents": [ "Male given names", "Given names", "Names", "All topics", "Proper nouns", "Terms by semantic function", "Fundamental", "Nouns", "Lemmas" ], "source": "w" }, { "kind": "other", "name": "Nepali terms with redundant transliterations", "parents": [ "Terms with redundant transliterations", "Entry maintenance" ], "source": "w" }, { "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w" }, { "kind": "other", "name": "Pages with entries", "parents": [], "source": "w" }, { "_dis": "38 45 11 0 6", "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w+disamb" }, { "_dis": "35 41 15 0 7", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" } ], "glosses": [ "a male given name" ], "id": "en-सरोज-ne-name-h8YdwBAs", "links": [ [ "given name", "given name" ] ] } ], "sounds": [ { "ipa": "[sʌɾo(d)z]" } ], "word": "सरोज" } { "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "1": "sa", "2": "adjective" }, "expansion": "सरोज • (saroja)", "name": "head" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "adj", "senses": [ { "categories": [ { "_dis": "38 45 11 0 6", "kind": "other", "name": "Pages with 3 entries", "parents": [], "source": "w+disamb" }, { "_dis": "35 41 15 0 7", "kind": "other", "name": "Pages with entries", "parents": [], "source": "w+disamb" }, { "_dis": "67 1 32", "kind": "other", "name": "Sanskrit entries with incorrect language header", "parents": [ "Entries with incorrect language header", "Entry maintenance" ], "source": "w+disamb" } ], "glosses": [ "produced or found in lakes and ponds (Tarkas.)" ], "id": "en-सरोज-sa-adj-b5m1Dzm0", "links": [ [ "produced", "produced" ], [ "found", "found" ], [ "lake", "lake" ], [ "pond", "pond" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" } { "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "id", "2": "seroja" }, "expansion": "Indonesian: seroja", "name": "desc" } ], "text": "Indonesian: seroja" } ], "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "g": "n" }, "expansion": "सरोज • (saroja) stem, n", "name": "sa-noun" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "noun", "senses": [ { "glosses": [ "a lotus (Kāv., VarBṛS.)" ], "id": "en-सरोज-sa-noun-r5KHj-ap", "links": [ [ "lotus", "lotus" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" } { "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "g": "m" }, "expansion": "सरोज • (saroja) stem, m", "name": "sa-noun" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "noun", "senses": [ { "glosses": [ "a prosodial foot containing 6 instants (according to some \"6 long syllables\") (Col.)" ], "id": "en-सरोज-sa-noun-aOkQZ~QT", "links": [ [ "prosodial", "prosodial" ], [ "foot", "foot" ], [ "instant", "instant" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" }
{ "categories": [ "Pages with 3 entries", "Pages with entries" ], "etymology_templates": [ { "args": { "1": "hi", "2": "sa", "3": "सरोज" }, "expansion": "Learned borrowing from Sanskrit सरोज (saroja)", "name": "lbor" } ], "etymology_text": "Learned borrowing from Sanskrit सरोज (saroja).", "forms": [ { "form": "saroj", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "hi-ndecl", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "cons-stem", "source": "declension", "tags": [ "class" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "direct", "singular" ] }, { "form": "सरोजें", "roman": "sarojẽ", "source": "declension", "tags": [ "direct", "plural" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "oblique", "singular" ] }, { "form": "सरोजों", "roman": "sarojõ", "source": "declension", "tags": [ "oblique", "plural" ] }, { "form": "सरोज", "roman": "saroj", "source": "declension", "tags": [ "singular", "vocative" ] }, { "form": "सरोजो", "roman": "sarojo", "source": "declension", "tags": [ "plural", "vocative" ] } ], "head_templates": [ { "args": { "g": "f" }, "expansion": "सरोज • (saroj) f", "name": "hi-proper noun" } ], "inflection_templates": [ { "args": { "1": "<F>" }, "name": "hi-ndecl" } ], "lang": "Hindi", "lang_code": "hi", "pos": "name", "senses": [ { "categories": [ "Hindi entries with incorrect language header", "Hindi female given names", "Hindi female given names from Sanskrit", "Hindi feminine consonant-stem nouns", "Hindi feminine nouns", "Hindi given names", "Hindi learned borrowings from Sanskrit", "Hindi lemmas", "Hindi proper nouns", "Hindi terms borrowed from Sanskrit", "Hindi terms derived from Sanskrit", "Hindi terms with IPA pronunciation", "Pages with 3 entries", "Pages with entries" ], "glosses": [ "a female given name, Saroj, from Sanskrit" ], "links": [ [ "given name", "given name" ], [ "Saroj", "Saroj#English" ] ] } ], "sounds": [ { "ipa": "/sə.ɾoːd͡ʒ/", "tags": [ "Delhi" ] }, { "ipa": "[sɐ.ɾoːd͡ʒ]", "tags": [ "Delhi" ] } ], "word": "सरोज" } { "categories": [ "Pages with 3 entries", "Pages with entries" ], "forms": [ { "form": "saroj", "tags": [ "romanization" ] }, { "form": "no-table-tags", "source": "declension", "tags": [ "table-tags" ] }, { "form": "ne-decl-noun-sg", "source": "declension", "tags": [ "inflection-template" ] }, { "form": "सरोज [sʌɾoz]", "source": "declension", "tags": [ "nominative", "singular" ] }, { "form": "सरोज [sʌɾodz]", "source": "declension", "tags": [ "nominative", "singular" ] }, { "form": "सरोजलाई [sʌɾozläi]", "source": "declension", "tags": [ "accusative", "singular" ] }, { "form": "सरोजलाई [sʌɾodzläi]", "source": "declension", "tags": [ "accusative", "singular" ] }, { "form": "instrumental", "source": "declension", "tags": [ "accusative" ] }, { "form": "ergative", "source": "declension", "tags": [ "accusative" ] }, { "form": "सरोजले [sʌɾozle]", "source": "declension", "tags": [ "singular" ] }, { "form": "सरोजले [sʌɾodzle]", "source": "declension", "tags": [ "singular" ] }, { "form": "सरोजलाई [sʌɾozläi]", "source": "declension", "tags": [ "dative", "singular" ] }, { "form": "सरोजलाई [sʌɾodzläi]", "source": "declension", "tags": [ "dative", "singular" ] }, { "form": "सरोजबाट [sʌɾozbäʈʌ]", "source": "declension", "tags": [ "ablative", "singular" ] }, { "form": "सरोजबाट [sʌɾodzbäʈʌ]", "source": "declension", "tags": [ "ablative", "singular" ] }, { "form": "सरोजको [sʌɾozko]", "source": "declension", "tags": [ "genitive", "singular" ] }, { "form": "सरोजको [sʌɾodzko]", "source": "declension", "tags": [ "genitive", "singular" ] }, { "form": "सरोजमा [sʌɾozmä]", "source": "declension", "tags": [ "locative", "singular" ] }, { "form": "सरोजमा [sʌɾodzmä]", "source": "declension", "tags": [ "locative", "singular" ] } ], "head_templates": [ { "args": {}, "expansion": "सरोज • (saroj)", "name": "ne-proper noun" } ], "inflection_templates": [ { "args": {}, "name": "ne-decl-noun-sg" } ], "lang": "Nepali", "lang_code": "ne", "pos": "name", "senses": [ { "categories": [ "Nepali entries with incorrect language header", "Nepali given names", "Nepali lemmas", "Nepali male given names", "Nepali proper nouns", "Nepali terms with IPA pronunciation", "Nepali terms with redundant transliterations", "Pages with 3 entries", "Pages with entries" ], "glosses": [ "a male given name" ], "links": [ [ "given name", "given name" ] ] } ], "sounds": [ { "ipa": "[sʌɾo(d)z]" } ], "word": "सरोज" } { "categories": [ "Pages with 3 entries", "Pages with entries", "Sanskrit adjectives", "Sanskrit compound terms", "Sanskrit entries with incorrect language header", "Sanskrit lemmas", "Sanskrit masculine nouns", "Sanskrit neuter nouns", "Sanskrit nouns", "Sanskrit nouns in Devanagari script", "Sanskrit terms with IPA pronunciation" ], "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "1": "sa", "2": "adjective" }, "expansion": "सरोज • (saroja)", "name": "head" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "adj", "senses": [ { "glosses": [ "produced or found in lakes and ponds (Tarkas.)" ], "links": [ [ "produced", "produced" ], [ "found", "found" ], [ "lake", "lake" ], [ "pond", "pond" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" } { "categories": [ "Pages with 3 entries", "Pages with entries", "Sanskrit adjectives", "Sanskrit compound terms", "Sanskrit entries with incorrect language header", "Sanskrit lemmas", "Sanskrit masculine nouns", "Sanskrit neuter nouns", "Sanskrit nouns", "Sanskrit nouns in Devanagari script", "Sanskrit terms with IPA pronunciation" ], "descendants": [ { "depth": 1, "templates": [ { "args": { "1": "id", "2": "seroja" }, "expansion": "Indonesian: seroja", "name": "desc" } ], "text": "Indonesian: seroja" } ], "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "g": "n" }, "expansion": "सरोज • (saroja) stem, n", "name": "sa-noun" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "noun", "senses": [ { "glosses": [ "a lotus (Kāv., VarBṛS.)" ], "links": [ [ "lotus", "lotus" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" } { "categories": [ "Pages with 3 entries", "Pages with entries", "Sanskrit adjectives", "Sanskrit compound terms", "Sanskrit entries with incorrect language header", "Sanskrit lemmas", "Sanskrit masculine nouns", "Sanskrit neuter nouns", "Sanskrit nouns", "Sanskrit nouns in Devanagari script", "Sanskrit terms with IPA pronunciation" ], "etymology_templates": [ { "args": { "1": "sa", "2": "सरस्", "3": "ज", "t1": "water", "t2": "born from, produced by" }, "expansion": "सरस् (saras, “water”) + ज (ja, “born from, produced by”)", "name": "compound" } ], "etymology_text": "From सरस् (saras, “water”) + ज (ja, “born from, produced by”).", "forms": [ { "form": "saroja", "tags": [ "romanization" ] } ], "head_templates": [ { "args": { "g": "m" }, "expansion": "सरोज • (saroja) stem, m", "name": "sa-noun" } ], "lang": "Sanskrit", "lang_code": "sa", "pos": "noun", "senses": [ { "glosses": [ "a prosodial foot containing 6 instants (according to some \"6 long syllables\") (Col.)" ], "links": [ [ "prosodial", "prosodial" ], [ "foot", "foot" ], [ "instant", "instant" ] ] } ], "sounds": [ { "ipa": "/sɐ.ɾɐw.d͡ʑɐ/", "tags": [ "Vedic" ] }, { "ipa": "/s̪ɐˈɾoː.d͡ʑɐ/", "tags": [ "Classical-Sanskrit" ] } ], "word": "सरोज" }
Download raw JSONL data for सरोज meaning in All languages combined (8.3kB)
{ "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: nominative", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: accusative", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2522", "msg": "rejected heuristic header: table cell identified as header based on style, BUT the cleaned text is not in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: instrumental/ergative, style: background:#eff7ff////NodeKind.TABLE_CELL", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: dative", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: ablative", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: genitive", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: locative", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" } { "called_from": "inflection/2466", "msg": "accepted heuristic header: table cell identified as header and given candidate status, AND the cleaned text is in LANGUAGES_WITH_CELLS_AS_HEADERS[Nepali]; cleaned text: Notes: * -को (-ko) becomes: ** -का (-kā) when followed by a plural noun. ** -की (-kī) when followed by a feminine noun.", "path": [ "सरोज" ], "section": "Nepali", "subsection": "proper noun", "title": "सरोज", "trace": "" }
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2025-01-18 from the enwiktionary dump dated 2025-01-01 using wiktextract (e4a2c88 and 4230888). 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.