See cham on Wiktionary
{ "antonyms": [ { "sense_index": "1.1", "word": "dżentelmen" }, { "sense_index": "1.2", "word": "szlachcic" }, { "sense_index": "1.2", "word": "arystokrata" }, { "sense_index": "1.2", "word": "magnat" } ], "categories": [ { "kind": "other", "name": "Polski (indeks)", "orig": "polski (indeks)", "parents": [], "source": "w" } ], "etymology_texts": [ "pol. Cham; od imienia biblijnego Chama (jednego z synów Noego)" ], "forms": [ { "form": "chamy", "sense_index": "1.1-2", "tags": [ "nominative", "plural" ] }, { "form": "chama", "sense_index": "1.1-2", "tags": [ "genitive", "singular" ] }, { "form": "chamów", "sense_index": "1.1-2", "tags": [ "genitive", "plural" ] }, { "form": "chamowi", "sense_index": "1.1-2", "tags": [ "dative", "singular" ] }, { "form": "chamom", "sense_index": "1.1-2", "tags": [ "dative", "plural" ] }, { "form": "chama", "sense_index": "1.1-2", "tags": [ "accusative", "singular" ] }, { "form": "chamów", "sense_index": "1.1-2", "tags": [ "accusative", "plural" ] }, { "form": "chamy", "sense_index": "1.1-2", "tags": [ "accusative", "plural" ] }, { "form": "chamem", "sense_index": "1.1-2", "tags": [ "instrumental", "singular" ] }, { "form": "chamami", "sense_index": "1.1-2", "tags": [ "instrumental", "plural" ] }, { "form": "chamie", "sense_index": "1.1-2", "tags": [ "locative", "singular" ] }, { "form": "chamach", "sense_index": "1.1-2", "tags": [ "locative", "plural" ] }, { "form": "chamie", "sense_index": "1.1-2", "tags": [ "vocative", "singular" ] }, { "form": "chamy", "sense_index": "1.1-2", "tags": [ "vocative", "plural" ] }, { "form": "chami", "sense_index": "1.1-2", "tags": [ "depreciative", "nominative", "vocative", "plural" ] } ], "lang": "język polski", "lang_code": "pl", "pos": "noun", "pos_text": "rzeczownik", "proverbs": [ { "word": "cham i prostak" }, { "word": "przysłowie: kto wyjdzie z chama na pana, niema gorszego gałgana" } ], "raw_tags": [ "męskoosobowy", "lub" ], "related": [ { "tags": [ "noun", "neuter" ], "word": "chamstwo" }, { "tags": [ "neuter" ], "word": "chamienie" }, { "tags": [ "neuter" ], "word": "schamienie" }, { "tags": [ "neuter" ], "word": "odchamianie" }, { "tags": [ "neuter" ], "word": "odchamienie" }, { "tags": [ "feminine" ], "word": "chamskość" }, { "tags": [ "feminine" ], "word": "forma żeńska chamka" }, { "tags": [ "feminine" ], "word": "chamica" }, { "tags": [ "feminine" ], "word": "chamówa" }, { "tags": [ "feminine" ], "word": "chamówka" }, { "tags": [ "diminutive", "masculine" ], "word": "chamek" }, { "tags": [ "masculine" ], "word": "chamuś" }, { "tags": [ "augmentative", "neuter" ], "word": "chamidło" }, { "tags": [ "neuter" ], "word": "chamisko" }, { "raw_tags": [ "czas.", "ndk." ], "word": "chamieć" }, { "raw_tags": [ "dk." ], "word": "schamieć" }, { "raw_tags": [ "ndk." ], "word": "odchamiać" }, { "raw_tags": [ "dk." ], "word": "odchamić" }, { "tags": [ "adjective" ], "word": "chamski" }, { "word": "chamowaty" }, { "tags": [ "adverb" ], "word": "chamsko" } ], "senses": [ { "examples": [ { "text": "Ten cham nawet się ze mną nie przywitał!" } ], "glosses": [ "osoba, która zachowuje się bezczelnie, ordynarnie, nie przestrzega podstawowych norm" ], "id": "pl-cham-pl-noun-jIT9eIdJ", "raw_tags": [ "obraź." ], "sense_index": "1.1", "tags": [ "pejorative" ] }, { "examples": [ { "text": "Cham powinien słuchać swojego pana, bo po to się urodził!" } ], "glosses": [ "człowiek niskiego stanu, chłop, parobek" ], "id": "pl-cham-pl-noun-ZhwKvrhd", "sense_index": "1.2", "tags": [ "obsolete", "scornfully" ] } ], "sounds": [ { "ipa": "xãm" }, { "ipa": "χãm", "tags": [ "Slavic-alphabet" ] }, { "audio": "Pl-cham.ogg", "mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/6/6e/Pl-cham.ogg/Pl-cham.ogg.mp3", "ogg_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Pl-cham.ogg" } ], "synonyms": [ { "sense_index": "1.1", "word": "bamber" }, { "sense_index": "1.1", "word": "burak" }, { "sense_index": "1.1", "word": "barbarzyńca" }, { "sense_index": "1.1", "word": "burek" }, { "sense_index": "1.1", "word": "chamidło" }, { "sense_index": "1.1", "word": "chamisko" }, { "sense_index": "1.1", "word": "chamskie nasienie" }, { "sense_index": "1.1", "word": "chamuś" }, { "sense_index": "1.1", "word": "gw. lwow. ćmok" }, { "sense_index": "1.1", "word": "gbur" }, { "sense_index": "1.1", "word": "gburzysko" }, { "sense_index": "1.1", "word": "grubianin" }, { "sense_index": "1.1", "word": "jaskiniowiec" }, { "sense_index": "1.1", "word": "kałmuk" }, { "sense_index": "1.1", "word": "nieokrzesaniec" }, { "sense_index": "1.1", "word": "ordynus" }, { "sense_index": "1.1", "word": "parobas" }, { "sense_index": "1.1", "word": "plebejusz" }, { "sense_index": "1.1", "word": "prostak" }, { "sense_index": "1.1", "word": "prymityw" }, { "sense_index": "1.1", "word": "troglodyta" }, { "sense_index": "1.1", "word": "żłób" }, { "sense_index": "1.2", "word": "plebejusz" }, { "sense_index": "1.2", "word": "prostak" } ], "tags": [ "animate", "masculine" ], "translations": [ { "lang": "angielski", "lang_code": "en", "sense_index": "1.1", "word": "lout" }, { "lang": "angielski", "lang_code": "en", "sense_index": "1.1", "word": "cad" }, { "lang": "białoruski", "lang_code": "be", "sense_index": "1.1", "tags": [ "feminine" ], "word": "хам" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.1", "tags": [ "common" ], "word": "bonderøv" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.1", "tags": [ "common" ], "word": "grobrian" }, { "lang": "hebrajski", "lang_code": "he", "roman": "gas ruach", "sense_index": "1.1", "tags": [ "masculine" ], "word": "גס רוח" }, { "lang": "jidysz", "lang_code": "yi", "roman": "cham", "sense_index": "1.1", "tags": [ "masculine" ], "word": "כאַם" }, { "lang": "jidysz", "lang_code": "yi", "roman": "grober fligl", "sense_index": "1.1", "tags": [ "masculine" ], "word": "גראָבער פֿליגל" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "cham" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "nipòcnik" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "nipòcoch" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "niegòdzëjôsz" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "niegòdzywc" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "sprostôk" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Rüpel" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Grobian" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Lümmel" }, { "lang": "rosyjski", "lang_code": "ru", "sense_index": "1.1", "tags": [ "masculine" ], "word": "хам" }, { "lang": "ukraiński", "lang_code": "uk", "sense_index": "1.1", "tags": [ "masculine" ], "word": "хам" }, { "lang": "wilamowski", "lang_code": "wym", "sense_index": "1.1", "tags": [ "masculine" ], "word": "priöestok" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "cafone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "zoticone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "screanzato" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "villano" }, { "lang": "włoski", "lang_code": "it", "raw_tags": [ "reg." ], "sense_index": "1.1", "tags": [ "masculine" ], "word": "burino" }, { "lang": "białoruski", "lang_code": "be", "sense_index": "1.2", "tags": [ "feminine" ], "word": "хам" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.2", "tags": [ "common" ], "word": "bonde" }, { "lang": "jidysz", "lang_code": "yi", "roman": "cham", "sense_index": "1.2", "tags": [ "masculine" ], "word": "כאַם" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.2", "word": "cham" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.2", "tags": [ "masculine" ], "word": "Bauer" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "cafone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "burino" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "villano" } ], "word": "cham" } { "categories": [ { "kind": "other", "name": "Język kaszubski", "parents": [], "source": "w" }, { "kind": "other", "name": "Kaszubski (indeks)", "orig": "kaszubski (indeks)", "parents": [], "source": "w" } ], "lang": "język kaszubski", "lang_code": "csb", "pos": "noun", "pos_text": "rzeczownik", "related": [ { "tags": [ "adjective" ], "word": "chamsczi" }, { "tags": [ "noun", "neuter" ], "word": "chamstwò" } ], "senses": [ { "glosses": [ "cham, prostak, niegodziwiec, buc" ], "id": "pl-cham-csb-noun-7AhxVmP~", "sense_index": "1.1", "tags": [ "pejorative" ] }, { "glosses": [ "cham" ], "id": "pl-cham-csb-noun-R37QuLk8", "sense_index": "1.2", "tags": [ "obsolete" ] } ], "synonyms": [ { "sense_index": "1.1", "word": "nipòcnik" }, { "sense_index": "1.1", "word": "nipòcoch" }, { "sense_index": "1.1", "word": "niegòdzëjôsz" }, { "sense_index": "1.1", "word": "niegòdzywc" }, { "sense_index": "1.1", "word": "sëri człowiek" }, { "sense_index": "1.1", "word": "sprostôk" }, { "sense_index": "1.1", "word": "bùc" }, { "sense_index": "1.1", "word": "bùcôk" }, { "sense_index": "1.1", "word": "baran" }, { "sense_index": "1.1", "word": "łãp" }, { "sense_index": "1.1", "word": "zawalëdroga" } ], "tags": [ "masculine" ], "word": "cham" }
{ "categories": [ "Język kaszubski", "kaszubski (indeks)" ], "lang": "język kaszubski", "lang_code": "csb", "pos": "noun", "pos_text": "rzeczownik", "related": [ { "tags": [ "adjective" ], "word": "chamsczi" }, { "tags": [ "noun", "neuter" ], "word": "chamstwò" } ], "senses": [ { "glosses": [ "cham, prostak, niegodziwiec, buc" ], "sense_index": "1.1", "tags": [ "pejorative" ] }, { "glosses": [ "cham" ], "sense_index": "1.2", "tags": [ "obsolete" ] } ], "synonyms": [ { "sense_index": "1.1", "word": "nipòcnik" }, { "sense_index": "1.1", "word": "nipòcoch" }, { "sense_index": "1.1", "word": "niegòdzëjôsz" }, { "sense_index": "1.1", "word": "niegòdzywc" }, { "sense_index": "1.1", "word": "sëri człowiek" }, { "sense_index": "1.1", "word": "sprostôk" }, { "sense_index": "1.1", "word": "bùc" }, { "sense_index": "1.1", "word": "bùcôk" }, { "sense_index": "1.1", "word": "baran" }, { "sense_index": "1.1", "word": "łãp" }, { "sense_index": "1.1", "word": "zawalëdroga" } ], "tags": [ "masculine" ], "word": "cham" } { "antonyms": [ { "sense_index": "1.1", "word": "dżentelmen" }, { "sense_index": "1.2", "word": "szlachcic" }, { "sense_index": "1.2", "word": "arystokrata" }, { "sense_index": "1.2", "word": "magnat" } ], "categories": [ "polski (indeks)" ], "etymology_texts": [ "pol. Cham; od imienia biblijnego Chama (jednego z synów Noego)" ], "forms": [ { "form": "chamy", "sense_index": "1.1-2", "tags": [ "nominative", "plural" ] }, { "form": "chama", "sense_index": "1.1-2", "tags": [ "genitive", "singular" ] }, { "form": "chamów", "sense_index": "1.1-2", "tags": [ "genitive", "plural" ] }, { "form": "chamowi", "sense_index": "1.1-2", "tags": [ "dative", "singular" ] }, { "form": "chamom", "sense_index": "1.1-2", "tags": [ "dative", "plural" ] }, { "form": "chama", "sense_index": "1.1-2", "tags": [ "accusative", "singular" ] }, { "form": "chamów", "sense_index": "1.1-2", "tags": [ "accusative", "plural" ] }, { "form": "chamy", "sense_index": "1.1-2", "tags": [ "accusative", "plural" ] }, { "form": "chamem", "sense_index": "1.1-2", "tags": [ "instrumental", "singular" ] }, { "form": "chamami", "sense_index": "1.1-2", "tags": [ "instrumental", "plural" ] }, { "form": "chamie", "sense_index": "1.1-2", "tags": [ "locative", "singular" ] }, { "form": "chamach", "sense_index": "1.1-2", "tags": [ "locative", "plural" ] }, { "form": "chamie", "sense_index": "1.1-2", "tags": [ "vocative", "singular" ] }, { "form": "chamy", "sense_index": "1.1-2", "tags": [ "vocative", "plural" ] }, { "form": "chami", "sense_index": "1.1-2", "tags": [ "depreciative", "nominative", "vocative", "plural" ] } ], "lang": "język polski", "lang_code": "pl", "pos": "noun", "pos_text": "rzeczownik", "proverbs": [ { "word": "cham i prostak" }, { "word": "przysłowie: kto wyjdzie z chama na pana, niema gorszego gałgana" } ], "raw_tags": [ "męskoosobowy", "lub" ], "related": [ { "tags": [ "noun", "neuter" ], "word": "chamstwo" }, { "tags": [ "neuter" ], "word": "chamienie" }, { "tags": [ "neuter" ], "word": "schamienie" }, { "tags": [ "neuter" ], "word": "odchamianie" }, { "tags": [ "neuter" ], "word": "odchamienie" }, { "tags": [ "feminine" ], "word": "chamskość" }, { "tags": [ "feminine" ], "word": "forma żeńska chamka" }, { "tags": [ "feminine" ], "word": "chamica" }, { "tags": [ "feminine" ], "word": "chamówa" }, { "tags": [ "feminine" ], "word": "chamówka" }, { "tags": [ "diminutive", "masculine" ], "word": "chamek" }, { "tags": [ "masculine" ], "word": "chamuś" }, { "tags": [ "augmentative", "neuter" ], "word": "chamidło" }, { "tags": [ "neuter" ], "word": "chamisko" }, { "raw_tags": [ "czas.", "ndk." ], "word": "chamieć" }, { "raw_tags": [ "dk." ], "word": "schamieć" }, { "raw_tags": [ "ndk." ], "word": "odchamiać" }, { "raw_tags": [ "dk." ], "word": "odchamić" }, { "tags": [ "adjective" ], "word": "chamski" }, { "word": "chamowaty" }, { "tags": [ "adverb" ], "word": "chamsko" } ], "senses": [ { "examples": [ { "text": "Ten cham nawet się ze mną nie przywitał!" } ], "glosses": [ "osoba, która zachowuje się bezczelnie, ordynarnie, nie przestrzega podstawowych norm" ], "raw_tags": [ "obraź." ], "sense_index": "1.1", "tags": [ "pejorative" ] }, { "examples": [ { "text": "Cham powinien słuchać swojego pana, bo po to się urodził!" } ], "glosses": [ "człowiek niskiego stanu, chłop, parobek" ], "sense_index": "1.2", "tags": [ "obsolete", "scornfully" ] } ], "sounds": [ { "ipa": "xãm" }, { "ipa": "χãm", "tags": [ "Slavic-alphabet" ] }, { "audio": "Pl-cham.ogg", "mp3_url": "https://upload.wikimedia.org/wikipedia/commons/transcoded/6/6e/Pl-cham.ogg/Pl-cham.ogg.mp3", "ogg_url": "https://commons.wikimedia.org/wiki/Special:FilePath/Pl-cham.ogg" } ], "synonyms": [ { "sense_index": "1.1", "word": "bamber" }, { "sense_index": "1.1", "word": "burak" }, { "sense_index": "1.1", "word": "barbarzyńca" }, { "sense_index": "1.1", "word": "burek" }, { "sense_index": "1.1", "word": "chamidło" }, { "sense_index": "1.1", "word": "chamisko" }, { "sense_index": "1.1", "word": "chamskie nasienie" }, { "sense_index": "1.1", "word": "chamuś" }, { "sense_index": "1.1", "word": "gw. lwow. ćmok" }, { "sense_index": "1.1", "word": "gbur" }, { "sense_index": "1.1", "word": "gburzysko" }, { "sense_index": "1.1", "word": "grubianin" }, { "sense_index": "1.1", "word": "jaskiniowiec" }, { "sense_index": "1.1", "word": "kałmuk" }, { "sense_index": "1.1", "word": "nieokrzesaniec" }, { "sense_index": "1.1", "word": "ordynus" }, { "sense_index": "1.1", "word": "parobas" }, { "sense_index": "1.1", "word": "plebejusz" }, { "sense_index": "1.1", "word": "prostak" }, { "sense_index": "1.1", "word": "prymityw" }, { "sense_index": "1.1", "word": "troglodyta" }, { "sense_index": "1.1", "word": "żłób" }, { "sense_index": "1.2", "word": "plebejusz" }, { "sense_index": "1.2", "word": "prostak" } ], "tags": [ "animate", "masculine" ], "translations": [ { "lang": "angielski", "lang_code": "en", "sense_index": "1.1", "word": "lout" }, { "lang": "angielski", "lang_code": "en", "sense_index": "1.1", "word": "cad" }, { "lang": "białoruski", "lang_code": "be", "sense_index": "1.1", "tags": [ "feminine" ], "word": "хам" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.1", "tags": [ "common" ], "word": "bonderøv" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.1", "tags": [ "common" ], "word": "grobrian" }, { "lang": "hebrajski", "lang_code": "he", "roman": "gas ruach", "sense_index": "1.1", "tags": [ "masculine" ], "word": "גס רוח" }, { "lang": "jidysz", "lang_code": "yi", "roman": "cham", "sense_index": "1.1", "tags": [ "masculine" ], "word": "כאַם" }, { "lang": "jidysz", "lang_code": "yi", "roman": "grober fligl", "sense_index": "1.1", "tags": [ "masculine" ], "word": "גראָבער פֿליגל" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "cham" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "nipòcnik" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "nipòcoch" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "niegòdzëjôsz" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "niegòdzywc" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.1", "tags": [ "masculine" ], "word": "sprostôk" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Rüpel" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Grobian" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.1", "tags": [ "masculine" ], "word": "Lümmel" }, { "lang": "rosyjski", "lang_code": "ru", "sense_index": "1.1", "tags": [ "masculine" ], "word": "хам" }, { "lang": "ukraiński", "lang_code": "uk", "sense_index": "1.1", "tags": [ "masculine" ], "word": "хам" }, { "lang": "wilamowski", "lang_code": "wym", "sense_index": "1.1", "tags": [ "masculine" ], "word": "priöestok" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "cafone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "zoticone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "screanzato" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.1", "tags": [ "masculine" ], "word": "villano" }, { "lang": "włoski", "lang_code": "it", "raw_tags": [ "reg." ], "sense_index": "1.1", "tags": [ "masculine" ], "word": "burino" }, { "lang": "białoruski", "lang_code": "be", "sense_index": "1.2", "tags": [ "feminine" ], "word": "хам" }, { "lang": "duński", "lang_code": "da", "sense_index": "1.2", "tags": [ "common" ], "word": "bonde" }, { "lang": "jidysz", "lang_code": "yi", "roman": "cham", "sense_index": "1.2", "tags": [ "masculine" ], "word": "כאַם" }, { "lang": "kaszubski", "lang_code": "csb", "sense_index": "1.2", "word": "cham" }, { "lang": "niemiecki", "lang_code": "de", "sense_index": "1.2", "tags": [ "masculine" ], "word": "Bauer" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "cafone" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "burino" }, { "lang": "włoski", "lang_code": "it", "sense_index": "1.2", "tags": [ "masculine" ], "word": "villano" } ], "word": "cham" }
Download raw JSONL data for cham meaning in All languages combined (8.9kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2025-02-22 from the plwiktionary dump dated 2025-02-21 using wiktextract (9e2b7d3 and f2e72e5). 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.