HTTP 200 OK
Allow: GET, POST, OPTIONS
Content-Type: application/json
Vary: Accept
{
"count": 4794,
"next": "https://metax.demo.fairdata.fi/v3/datasets?format=api&limit=20&offset=4780",
"previous": "https://metax.demo.fairdata.fi/v3/datasets?format=api&limit=20&offset=4740",
"results": [
{
"id": "e6b0fd42-0312-4256-8cad-29f5c3bf1550",
"access_rights": {
"id": "d59dd67b-eb63-44ac-9a31-446bba36c2aa",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2023032704",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "5a1173d6-aad0-4361-a415-9caf9ac13fb5",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "1af1c4d9-f070-488e-a710-d27e65cf87bb",
"pref_label": {
"en": "Kansalliskirjasto",
"fi": "Kansalliskirjasto",
"sv": "Kansalliskirjasto",
"und": "Kansalliskirjasto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901-H981",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization",
"parent": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
},
{
"id": "7b89dba9-68a9-4af0-a9f1-4e877f5bf1e7",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "0d6baff0-c9d9-4bb6-8cc0-6e2589d457dc",
"roles": [
"curator"
],
"person": {
"id": "8851600a-19f8-4037-b190-cd3002a4ac9a",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "This resource is available via Korp in Kielipankki – the Language Bank of Finland.\n\nThe corpus consists of Finnish newspapers and magazines starting from 1771 up to 2021, compiled by the National Library of Finland.\n\nFor this new version, the data of the previous version (Finnish and Swedish) was checked with the HeLI-OTS language identifier. Parts of texts, which do not contain Finnish, were removed from this corpus. On the other hand, texts from the Swedish part of KLK, which contain Finnish, where added to this corpus.\n\nThe new version consists of text elements, where at least one sentence element was identified as being in Finnish, from these three sources:\n\n - KLK-fi, version 1 (http://urn.fi/urn:nbn:fi:lb-2016050302)\n - KLK-sv, version 1 (http://urn.fi/urn:nbn:fi:lb-2016050301)\n - new data from the National Library (not previously available in the Language Bank, may cover any time period, just more recently OCR'd)\n\nThe text elements are enriched with a 'version_added' attribute, which identifies the source.\n\nFor a listing of the newspapers and magazines contained in this resource, please see the Documentation."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-202009152",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "The Finnish Sub-corpus of the Newspaper and Periodical Corpus of the National Library of Finland version 2, Korp",
"fi": "Kansalliskirjaston sanoma- ja aikakauslehtikokoelman suomenkielinen osakorpus versio 2, Korp"
},
"created": "2023-12-13T00:00:00Z",
"modified": "2024-12-04T13:10:40Z",
"dataset_versions": [
{
"id": "e6b0fd42-0312-4256-8cad-29f5c3bf1550",
"title": {
"en": "The Finnish Sub-corpus of the Newspaper and Periodical Corpus of the National Library of Finland version 2, Korp",
"fi": "Kansalliskirjaston sanoma- ja aikakauslehtikokoelman suomenkielinen osakorpus versio 2, Korp"
},
"persistent_identifier": "urn:nbn:fi:lb-202009152",
"state": "published",
"created": "2023-12-13T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "0fcdc3af-a26a-4243-9842-7adf657eb6e5",
"access_rights": {
"id": "c52d50ff-e55c-4bef-b9cd-b0b82fd68e61",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2022050901",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "108b0eb5-9168-4f50-8e21-2cd5429bf222",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "6112394a-531a-4dcd-b011-80c2936c0573",
"pref_label": {
"en": "Finnish Broadcasting Company (Yle)",
"fi": "Yleisradio Oy"
},
"homepage": {
"url": "https://yle.fi/"
},
"email": "<hidden>"
}
},
{
"id": "5f081348-5f15-42f2-bf64-b8466d1d1e9b",
"roles": [
"curator"
],
"person": {
"id": "d95e233a-a972-4e6a-ab34-e1bde1f05441",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "42d09d14-8a1f-4e9d-b63f-7076e08709ca",
"roles": [
"publisher"
],
"organization": {
"id": "19549ae7-044d-4573-b83b-56af60cf43cd",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus is available for download in Kielipankki - the Language Bank of Finland.\n\nThis dataset consists of the Yle Selkokieliset uutiset in Finnish (Yle Easy-to-read Finnish News). The dataset was created from the contents of the Yle News Archive for the language code \"fi\" for each month from the year 2011 to the year 2018, inclusive, harvested on 2019-03-08 by FIN-CLARIN. The documents were found by using the publisher name \"Yle Selkouutiset\". Please note, that no such articles occurred before 2014.\n\nThe Easy-to-read-Finnish news are available on the Yle website https://yle.fi/uutiset/osasto/selkouutiset/\n\nThe corpus is available in the Language Bank download service at korp.csc.fi/download in the VRT format.",
"fi": "Korpus sisältää Ylen uutisarkiston selkouutiset vuosilta 2011-2018. Alkuperäinen aineisto, Ylen suomenkielinen uutisarkisto 2011-2018, lähdeaineisto (pysyväistunniste http://urn.fi/urn:nbn:fi:lb-2017070501) on harvestoitu Ylen uutisarkistosta 8.3.2019 kielikoodilla \"fi\". Selkouutisten korpus on koostettu Ylen suomenkielisen uutisarkiston aineistossa mukana olevista selkouutisista. Ylen verkkosivustolla https://yle.fi selkouutiset löytyvät sivulta https://yle.fi/uutiset/osasto/selkouutiset/\n\nAineisto on ladattavissa Kielipankin latauspalvelussa korp.csc.fi/download VRT-formaatissa."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2020021115",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Yle News Archive Easy-to-read Finnish 2011-2018, VRT",
"fi": "Ylen suomenkielisen uutisarkiston selkouutiset 2011-2018, VRT"
},
"created": "2023-04-27T00:00:00Z",
"modified": "2024-12-04T13:09:59Z",
"dataset_versions": [
{
"id": "0fcdc3af-a26a-4243-9842-7adf657eb6e5",
"title": {
"en": "Yle News Archive Easy-to-read Finnish 2011-2018, VRT",
"fi": "Ylen suomenkielisen uutisarkiston selkouutiset 2011-2018, VRT"
},
"persistent_identifier": "urn:nbn:fi:lb-2020021115",
"state": "published",
"created": "2023-04-27T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "896e99e5-115d-4565-aea4-26e84305b5d4",
"access_rights": {
"id": "c13393d6-c492-481d-82e8-ae8c31438152",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "05b76a9e-8224-49e8-83b7-aa7381aa76cf",
"roles": [
"creator",
"publisher",
"rights_holder"
],
"organization": {
"id": "541c236a-a23c-4bd6-bdc8-34777a5ac72e",
"pref_label": {
"en": "The Parliament of Finland"
},
"homepage": {
"url": "http://web.eduskunta.fi/Resource.phx/parliament/index.htx?lng=en"
},
"email": "<hidden>"
}
},
{
"id": "362d84ca-ac94-4bb5-848b-111129c1b8aa",
"roles": [
"curator"
],
"person": {
"id": "f7c6ea7d-dd7a-461f-9725-d8433f8f446b",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "Official transcripts of the Plenary Sessions of the Parliament of Finland, edited and published by the Parliament of FInland.",
"fi": "Suomen eduskunnan toimittamat täysistuntojen viralliset pöytäkirjat."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
},
{
"id": "9135785b-bb66-471b-a379-1413861eff08",
"url": "http://lexvo.org/id/iso639-3/swe",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Swedish",
"fi": "ruotsi",
"sv": "svenska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2019111921",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Official transcripts of the Plenary Sessions of the Parliament of Finland (an accumulating archive)",
"fi": "Eduskunnan täysistuntojen viralliset pöytäkirjat (karttuva arkisto)"
},
"created": "2023-04-05T00:00:00Z",
"modified": "2024-12-04T13:09:07Z",
"dataset_versions": [
{
"id": "896e99e5-115d-4565-aea4-26e84305b5d4",
"title": {
"en": "Official transcripts of the Plenary Sessions of the Parliament of Finland (an accumulating archive)",
"fi": "Eduskunnan täysistuntojen viralliset pöytäkirjat (karttuva arkisto)"
},
"persistent_identifier": "urn:nbn:fi:lb-2019111921",
"state": "published",
"created": "2023-04-05T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "90246d1b-8510-4eba-92c5-378e666db298",
"access_rights": {
"id": "9abaacf5-5597-45bd-a97a-87b1a6684ceb",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "72f88b51-34e2-494a-a12f-c563a70a0e4a",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "ff998b85-976f-48f7-a0eb-7de21da395c1",
"name": "Tatu Huovilainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "1f062cf5-e277-4c3b-960a-306234f419c1",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "2dd1d63c-92d9-42b8-b21c-93eb2764c7d9",
"roles": [
"curator"
],
"person": {
"id": "43ff26bf-d464-47c8-a267-106e3c6bf710",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The Finnish OpenSubtitles 2017 source material corpus is available for download.\n\nThe corpus contains Finnish subtitles for movies and TV-series from http://www.opensubtitles.org/ The corpus is a derivative of the [OPUS OpenSubtitles2018](http://opus.nlpl.eu/OpenSubtitles2018.php) multilingual corpus. Information on the material processing up to sentence splitting can be found in the original publication Lison & Tiedemann (2016). The corpus has been tokenized and annotated with morpho-syntactic analysis produced with the [Turku Dependency Parser](http://turkunlp.github.io/Finnish-dep-parser/). \n\nP. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)\n\nLicense: CC BY https://creativecommons.org/licenses/by/4.0/",
"fi": "Suomenkielinen OpenSubtitles 2017 lähdemateriaali on saatavilla Kielipankin latauspalvelussa.\n\nAineisto kattaa Opensubtitles.org sivuston jakamat elokuvien ja tv-ohjelmien suomenkieliset tekstitykset. Aineisto on johdannainen monikielisestä Opensubtitles2018 korpuksesta (http://opus.nlpl.eu/OpenSubtitles2018.php) Aineisto on jaettu lähteisiin ja lauseisiin. Lauseet on morfosyntaktisesti jäsennetty käyttäen Turku BioNLP -ryhmän kehittämää dependenssijäsennintä (http://turkunlp.github.io/Finnish-dep-parser/).\n\nLisenssi: CC BY https://creativecommons.org/licenses/by/4.0/"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2019110801",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Finnish OpenSubtitles 2017, source",
"fi": "Suomenkielinen OpenSubtitles 2017, lähdemateriaali"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T13:08:57Z",
"dataset_versions": [
{
"id": "90246d1b-8510-4eba-92c5-378e666db298",
"title": {
"en": "Finnish OpenSubtitles 2017, source",
"fi": "Suomenkielinen OpenSubtitles 2017, lähdemateriaali"
},
"persistent_identifier": "urn:nbn:fi:lb-2019110801",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "fbec51ce-1279-4002-8171-5f52cb51de89",
"access_rights": {
"id": "ee89888e-dc2f-4d17-b386-78dd19a2373e",
"license": [
{
"id": "fc8a7008-cf5e-4df1-9e05-0145d445c80e",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN RES (Restricted) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "41b4ff93-e15e-4829-8553-49e4ef079d69",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restricted access due to other reasons",
"fi": "Saatavuutta rajoitettu muulla perusteella",
"sv": "Begränsad åtkomst av övriga skäl"
}
}
]
},
"actors": [
{
"id": "386b3d55-22b9-4e0e-a833-de02c78101d1",
"roles": [
"creator",
"publisher",
"rights_holder"
],
"organization": {
"id": "4599eee9-5e9d-446e-9d4d-449b1819cff4",
"pref_label": {
"en": "University of Eastern Finland",
"fi": "Itä-Suomen yliopisto",
"sv": "Östra Finlands universitet",
"und": "Itä-Suomen yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/10088",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "b7cfa61d-3dfc-4f08-b0df-9fa5b5039a50",
"roles": [
"curator"
],
"person": {
"id": "1559cc1f-b9a6-4189-8437-c603a9d668e1",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The Corpus of Translated Finnish has been compiled in 1999 in the University of Eastern Finland (University of Joensuu at the time and it's School of Translation Studies) in the project Translation Universals led by professor Anna Mauranen.\n\nThe corpus comprises two parts: texts originally written in Finnish and texts tranlated into Finnish from different languages. The following text types are represented in the corpus: academic texts, literature, childrens' literature, biography, popular literature and fiction, detective fiction and popular science.\n\nThe paragraphs have been scrambled within each text.",
"fi": "Käännössuomen korpus on koostettu vuonna 1999 nykyisessä Itä-Suomen yliopistossa (silloisessa Joensuun yliopistossa sen kansainvälisen viestinnän laitoksella) Suomen Akatemian professori Anna Maurasen johtamassa tutkimushankkeessa Käännössuomi ja kääntämisen universaalit. \n\nKorpus sisältää kaksi osaa: aluperin suomeksi kirjoitettua kieltä (alkusuomi) ja eri kielistä käännettyä kieltä (käännössuomi). Seuraavat tekstilajit ovat edustettuina aineistoissa: akateemiset tekstit, kaunokirjallisuus, lastenkirjallisuus, biografia, populaarikirjallisuus, viihdekirjallisuus, dekkarikirjallisuus ja tietokirjallisuus.\n\nKappaleet on sekoitettu kunkin tekstin sisällä."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2019100801",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Corpus of Translated Finnish, Korp",
"fi": "Käännössuomen korpus, Korp"
},
"created": "2023-03-22T00:00:00Z",
"modified": "2024-12-04T13:08:50Z",
"dataset_versions": [
{
"id": "fbec51ce-1279-4002-8171-5f52cb51de89",
"title": {
"en": "Corpus of Translated Finnish, Korp",
"fi": "Käännössuomen korpus, Korp"
},
"persistent_identifier": "urn:nbn:fi:lb-2019100801",
"state": "published",
"created": "2023-03-22T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "bb782df6-5750-48d0-b510-d866f4063790",
"access_rights": {
"id": "5d4f88e2-69a1-412c-b2dc-664541ebcb8d",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "55b72089-62b6-4c35-81c0-266551357c9d",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "452daf3d-7f53-4f24-bd74-6121f6270df2",
"name": "Tatu Huovilainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "794310e4-2556-4df7-a4da-3527b9594deb",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "ec1b5312-e529-4d40-aacb-86d3db9edb2b",
"roles": [
"curator"
],
"person": {
"id": "82d16709-ca41-48fb-bec1-043f16b828df",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus is available in Kielipankki through the Interface Korp.\nThe corpus contains Finnish subtitles for movies and TV-series from http://www.opensubtitles.org/ The corpus is a derivative of the [OPUS OpenSubtitles2018](http://opus.nlpl.eu/OpenSubtitles2018.php) multilingual corpus. Information on the material processing up to sentence splitting can be found in the original publication Lison & Tiedemann (2016). The corpus has been tokenized and annotated with morpho-syntactic analysis produced with the [Turku Dependency Parser](http://turkunlp.github.io/Finnish-dep-parser/). P. Lison and J. Tiedemann, 2016, OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016)",
"fi": "Aineisto kattaa Opensubtitles.org sivuston jakamat elokuvien ja tv-ohjelmien suomenkieliset tekstitykset. Aineisto on johdannainen\nmonikielisestä Opensubtitles2018 korpuksesta (http://opus.nlpl.eu/OpenSubtitles2018.php) Aineisto on jaettu lähteisiin ja lauseisiin. Lauseet on morfosyntaktisesti jäsennetty käyttäen Turku Dependenssi jäsennintä (http://turkunlp.github.io/Finnish-dep-parser/)"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2018060403",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Finnish OpenSubtitles 2017, Kielipankki Korp Version",
"fi": "Suomenkielinen OpenSubtitles 2017, Kielipankin Korp-versio"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T13:07:36Z",
"dataset_versions": [
{
"id": "bb782df6-5750-48d0-b510-d866f4063790",
"title": {
"en": "Finnish OpenSubtitles 2017, Kielipankki Korp Version",
"fi": "Suomenkielinen OpenSubtitles 2017, Kielipankin Korp-versio"
},
"persistent_identifier": "urn:nbn:fi:lb-2018060403",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "5ad89da7-35dd-49f2-9343-aaffe7e53c85",
"access_rights": {
"id": "cf18700c-4b70-4260-a2ad-bd7cfb00dc01",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "433c01a4-2210-4f11-8534-b0a87b00ca4f",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "e1936a88-feaa-4f02-b1ed-4632ecf47aa3",
"name": "Tatu Huovilainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "5ad92795-ad01-498e-ae2e-a93152a350f7",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "f58a4829-65ce-40dd-95c9-b4c218cd79ff",
"roles": [
"curator"
],
"person": {
"id": "cee96ed5-c867-43a4-8573-a407db5d57d4",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The Finnish Wikipedia 2017 Corpus will be available in the concordance tool Korp.\nThe corpus contains all the Finnish articles from the online encyclopedia Wikipedia available in 1 January 2018.\nThe text parts of the articles have been extracted from [Wikipedia Dumps](https://dumps.wikimedia.org/) with [WikiExtractor](https://github.com/attardi/wikiextractor).\nThe corpus has been tokenized and annotated with morpho-syntactic analysis produced with the [Turku Dependency Parser](http://turkunlp.github.io/Finnish-dep-parser/)",
"fi": "Aineisto kattaa Wikipedian suomenkielisen artikkelien leipätekstit vuoden 2017 lopulta. Tekstit on eristetty Wikipedian tarjoamista kielikohtaisista kokonaisaineistoista (https://dumps.wikimedia.org/) Aineisto on jaettu arikkeleihin, kappaleisiin ja lauseisiin. Lauseet on morfosyntaktisesti jäsennetty käyttäen Turku Dependenssi -jäsennintä (http://turkunlp.github.io/Finnish-dep-parser/)"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2018060401",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Finnish Wikipedia 2017, Korp",
"fi": "Suomenkielinen Wikipedia 2017, Korp"
},
"created": "2022-09-02T00:00:00Z",
"modified": "2024-12-04T13:07:32Z",
"dataset_versions": [
{
"id": "5ad89da7-35dd-49f2-9343-aaffe7e53c85",
"title": {
"en": "Finnish Wikipedia 2017, Korp",
"fi": "Suomenkielinen Wikipedia 2017, Korp"
},
"persistent_identifier": "urn:nbn:fi:lb-2018060401",
"state": "published",
"created": "2022-09-02T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "361071da-9b06-42f5-8b0c-aacbe03aa413",
"access_rights": {
"id": "b8d501a6-3299-4aef-b089-fc3431d26ad0",
"license": [
{
"id": "8ed4c438-c01a-45a6-af3b-60eb50245ccb",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-NC-2.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution-NonCommercial 2.0 Generic (CC BY-NC 2.0",
"fi": "Creative Commons Nimeä-EiKaupallinen 2.0 Yleinen (CC BY-NC 2.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "3b3a2807-a5b1-4ecc-9903-bae58fd9ae3b",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "889efbbf-c8be-4b39-a0c1-612133704c2e",
"name": "Mathias Creutz",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "fa05e2d3-f23c-457d-8fc7-003297fe471d",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "8668faa6-1947-4ba2-8fdc-d0df89c20447",
"roles": [
"curator"
],
"person": {
"id": "e5a44ed4-f993-4511-a95a-d292d340f2f4",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "Opusparcus is a paraphrase corpus for six European languages: German, English, Finnish, French, Russian, and Swedish. The paraphrases are extracted from the OpenSubtitles2016 corpus, which contains subtitles from movies and TV shows. \n\nThe data in Opusparcus has been extracted from OpenSubtitles2016 (http://opus.nlpl.eu/OpenSubtitles2016.php) which is in turn based on data from http://www.opensubtitles.org/.\n\nFor each target language, the Opusparcus data have been partitioned into three types of data sets: training, development and test sets. The training sets are large, consisting of millions of sentence pairs, and have been compiled automatically, with the help of probabilistic ranking functions. The development and test sets consist of sentence pairs that have been annotated manually; each set contains approximately 1000 sentence pairs that have been verified to be acceptable paraphrases by two annotators.\n\nOpusparcus is available for download at the Language Bank of Finland. The README file in the download folder contains detailed descriptions of the data sets. \n\nPlease cite the following paper in any work that utilizes any part of the Opusparcus corpus.\n\nMathias Creutz (2018). Open Subtitles Paraphrase Corpus for Six Languages. In Proceedings of the 11th edition of the Language Resources and Evaluation Conference (LREC 2018), 7-12 May, Miyazaki, Japan."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
},
{
"id": "afcd3a6b-e6cb-4d2b-b31a-6579301f203f",
"url": "http://lexvo.org/id/iso639-3/rus",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Russian",
"fi": "venäjä",
"sv": "ryska"
}
},
{
"id": "8f8d38be-f5ee-490f-a33a-c8ddceef9785",
"url": "http://lexvo.org/id/iso639-3/eng",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "English",
"fi": "englanti",
"sv": "engelska"
}
},
{
"id": "bf6634d9-18cf-48c9-b015-3426d21c27c6",
"url": "http://lexvo.org/id/iso639-3/fra",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "French",
"fi": "ranska",
"sv": "franska"
}
},
{
"id": "9135785b-bb66-471b-a379-1413861eff08",
"url": "http://lexvo.org/id/iso639-3/swe",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Swedish",
"fi": "ruotsi",
"sv": "svenska"
}
},
{
"id": "dd743e2b-f3ea-45fc-941e-c92d078e7726",
"url": "http://lexvo.org/id/iso639-3/deu",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "German",
"fi": "saksa",
"sv": "tyska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2018021221",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Opusparcus: Open Subtitles Paraphrase Corpus for Six Languages (version 1.0)"
},
"created": "2023-04-05T00:00:00Z",
"modified": "2024-12-04T13:07:13Z",
"dataset_versions": [
{
"id": "361071da-9b06-42f5-8b0c-aacbe03aa413",
"title": {
"en": "Opusparcus: Open Subtitles Paraphrase Corpus for Six Languages (version 1.0)"
},
"persistent_identifier": "urn:nbn:fi:lb-2018021221",
"state": "published",
"created": "2023-04-05T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "207f1e82-c73f-46ef-9462-435f4dc55c2c",
"access_rights": {
"id": "532cce3b-c05d-4235-864c-dec3a7cb1bda",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "61d8fd85-9f7d-4ee4-9d5e-dad3852a77ad",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "5b171a59-e5b4-4cd3-96cc-4c38b451f0d4",
"pref_label": {
"en": "Prime Minister's Office"
},
"homepage": {
"url": "http://vnk.fi/en/frontpage"
},
"email": "<hidden>"
}
},
{
"id": "371c8d96-b189-4cd4-8f26-6e3afd61dd6c",
"roles": [
"curator"
],
"person": {
"id": "0171294f-c2af-405b-8b0d-b7b02afabe68",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "0e52a03b-c3d3-45ab-bc0b-8a784000c059",
"roles": [
"publisher"
],
"organization": {
"id": "15d05bfb-b7a0-4de1-8fbb-c9cd9115b348",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The \"Hallituskausi 2011–2015\" translation memory is intended for those translating administrative texts between Finnish and English. It includes key policy reports published by the Finnish ministries on their websites during the ongoing electoral period. The memory features some 11,000 Finnish-to-English translation segments.\n\nThe translation memory runs in a SDL Trados Studio programme. \n\nThe translation segments may contain errors due to the technical conversion process (for example, additional or missing hyphens which could affect the search function). \n\nThe translation memory is for reference use only. Use of the memory calls for case-by-case consideration and it must never be applied as such.\n\nThe Prime Minister’s Office is not responsible for any translation or other errors in the translation memory.\n\nThe is available for download at https://kielipankki.fi/download/"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
},
{
"id": "8f8d38be-f5ee-490f-a33a-c8ddceef9785",
"url": "http://lexvo.org/id/iso639-3/eng",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "English",
"fi": "englanti",
"sv": "engelska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2017090403",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "The \"Hallituskausi 2011–2015\" Translation Memory"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T13:06:39Z",
"dataset_versions": [
{
"id": "207f1e82-c73f-46ef-9462-435f4dc55c2c",
"title": {
"en": "The \"Hallituskausi 2011–2015\" Translation Memory"
},
"persistent_identifier": "urn:nbn:fi:lb-2017090403",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "2d3fcfc9-f17c-4777-b2f1-7e88bb747a34",
"access_rights": {
"id": "08d7c3d4-99d9-4e2f-a691-ab9e71123100",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "13465057-5ec3-4b08-a198-c701b3d4d42f",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "238666d0-57ac-4522-8420-a5310d8e6dc0",
"pref_label": {
"en": "Prime Minister's Office"
},
"homepage": {
"url": "http://vnk.fi/en/frontpage"
},
"email": "<hidden>"
}
},
{
"id": "cc0807e2-c101-4c0e-9586-ff36dbdf6dee",
"roles": [
"curator"
],
"person": {
"id": "7d488683-d043-4d55-9d45-19e49f4cd069",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "5e0b3cf2-cfe6-442d-9bfd-4adf2a0c157b",
"roles": [
"publisher"
],
"organization": {
"id": "a92e4c7b-2cc3-4172-81c5-ea510641e32c",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The \"Hallituskausi 2007–2011\" translation memory is intended for those translating administrative texts between Finnish and English. It includes key policy reports published by the Finnish ministries on their websites. The memory features some 58,000 Finnish-to-English translation segments.\n\nThe tmx format requires a SDL Trados Studio programme. \n\nThe translation segments may contain errors due to the technical conversion process (for example, additional or missing hyphens which could affect the search function). \n\nThe translation memory is for reference use only. Use of the memory calls for case-by-case consideration and it must never be applied as such.\n\nThe Prime Minister’s Office is not responsible for any translation or other errors in the translation memory. \n\nThe resource will be made available for download at https://kielipankki.fi/download/"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
},
{
"id": "8f8d38be-f5ee-490f-a33a-c8ddceef9785",
"url": "http://lexvo.org/id/iso639-3/eng",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "English",
"fi": "englanti",
"sv": "engelska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2017090402",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "The \"Hallituskausi 2007–2011\" Translation Memory"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T13:06:35Z",
"dataset_versions": [
{
"id": "2d3fcfc9-f17c-4777-b2f1-7e88bb747a34",
"title": {
"en": "The \"Hallituskausi 2007–2011\" Translation Memory"
},
"persistent_identifier": "urn:nbn:fi:lb-2017090402",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "0f20081d-e133-45c3-a1be-8570f66ca094",
"access_rights": {
"id": "f387358a-989e-45af-8bb5-d78aaeab43e9",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2022050901",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "7838e423-5a46-4ef2-8847-76c57a197cf1",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "5aa2870a-1e84-4a01-a12e-34a7866c4409",
"pref_label": {
"en": "Finnish Broadcasting Company (Yle)",
"fi": "Yleisradio Oy"
},
"homepage": {
"url": "https://yle.fi/"
},
"email": "<hidden>"
}
},
{
"id": "653c49fd-663f-4394-bf68-6b403bb2c146",
"roles": [
"curator"
],
"person": {
"id": "2820f147-52ef-4432-a455-91568d2ceb23",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "2b2c1d86-0cf9-4fe6-8022-a21ee4eb025c",
"roles": [
"publisher"
],
"organization": {
"id": "507dc512-0be4-457c-a555-958c947c1062",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus, containing the articles from YLE https://yle.fi from 2011-2018, is available at korp.csc.fi/download"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2017070501",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Yle Finnish News Archive 2011-2018, source",
"fi": "Ylen suomenkielinen uutisarkisto 2011-2018, lähdeaineisto"
},
"created": "2022-12-17T00:00:00Z",
"modified": "2024-12-04T13:06:25Z",
"dataset_versions": [
{
"id": "0f20081d-e133-45c3-a1be-8570f66ca094",
"title": {
"en": "Yle Finnish News Archive 2011-2018, source",
"fi": "Ylen suomenkielinen uutisarkisto 2011-2018, lähdeaineisto"
},
"persistent_identifier": "urn:nbn:fi:lb-2017070501",
"state": "published",
"created": "2022-12-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "79ed8e8b-7370-4413-97ea-26455c6e738e",
"access_rights": {
"id": "90305489-f508-4020-8997-c80a2abf1f8d",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2015041301",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "f92b4aa9-f9fd-43db-bc1c-feee6babe2e9",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "323ce425-d63e-486c-8278-d95b920dc2fb",
"name": "Paavo Alku",
"email": "<hidden>"
},
"organization": {
"id": "2f9f9011-4061-4a93-96af-768471abada7",
"pref_label": {
"en": "Aalto University",
"fi": "Aalto-yliopisto",
"sv": "Aalto-universitetet",
"und": "Aalto-yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/10076",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "b7577837-3230-434b-94d5-4139ca2a11b7",
"roles": [
"curator"
],
"person": {
"id": "668fbf72-28ef-4d58-8c23-62d2b972d423",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "5971d7b2-f707-4855-8e54-a9eea3321d8c",
"roles": [
"publisher"
],
"organization": {
"id": "acdb7fff-aa12-45bf-a1f6-9f2a8b95233b",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus was available via the LAT platform in Kielipankki - the Language Bank of Finland until December 2020. Since the LAT platform was discontinued, this corpus version can no longer be used, but a downloadable version of the same content will be maintained (see Relations). Further details about the most recent version are available on the info page of this corpus family (https://www.kielipankki.fi/aineistot/aku-egg) \n\nThe corpus contains continuous speech during which glottal activity was recorded by means of electroglottography.\n\nLicense details: http://urn.fi/urn:nbn:fi:lb-2015041301.\n\nlog\n26.11.2018 link http://islrn.org/resources/604-045-695-230-7 removed",
"fi": "Tämä aineisto oli saatavilla Kielipankin LAT-alustan kautta joulukuuhun 2020 saakka, jolloin LAT-alusta poistui käytöstä. Aineistosta on kuitenkin saatavilla vastaavan sisältöinen ladattava versio (ks. Relations). Lisätietoja löytyy aineiston tietosivulta Kielipankissa (ks. https://www.kielipankki.fi/aineistot/aku-egg).\n\nKorpus sisältää jatkuvaa puhetta, jonka aikana on rekisteröity kurkunpään (äänihuulten) toimintaa elektroglottografian avulla.\n\nLisätietoa kielivaran lisenssistä: http://urn.fi/urn:nbn:fi:lb-2015041301\n\n\nlog\n26.11.2018 linkki http://islrn.org/resources/604-045-695-230-7 poistettu"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-20140730182",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Speech and EGG (Electroglottography) Simultaneous Recordings",
"fi": "Puheen ja EGG:n samanaikaiset tallenteet"
},
"created": "2023-04-05T00:00:00Z",
"modified": "2024-12-04T13:03:19Z",
"dataset_versions": [
{
"id": "79ed8e8b-7370-4413-97ea-26455c6e738e",
"title": {
"en": "Speech and EGG (Electroglottography) Simultaneous Recordings",
"fi": "Puheen ja EGG:n samanaikaiset tallenteet"
},
"persistent_identifier": "urn:nbn:fi:lb-20140730182",
"state": "published",
"created": "2023-04-05T00:00:00Z",
"version": 1
}
],
"published_revision": 15,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "e5324440-ed23-4c52-b914-a04f5e51f814",
"access_rights": {
"id": "0947af4e-7f2c-4dd0-b7a6-003b99176058",
"license": [
{
"id": "fc8a7008-cf5e-4df1-9e05-0145d445c80e",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN RES (Restricted) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "41b4ff93-e15e-4829-8553-49e4ef079d69",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restricted access due to other reasons",
"fi": "Saatavuutta rajoitettu muulla perusteella",
"sv": "Begränsad åtkomst av övriga skäl"
}
}
]
},
"actors": [
{
"id": "d42a70c7-e215-4798-ad84-7bcb6d0542dd",
"roles": [
"creator"
],
"person": {
"id": "7bc01893-132c-41d0-9408-ad03fddc890b",
"name": "Matti Rahkonen",
"email": "<hidden>"
},
"organization": {
"id": "bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a",
"pref_label": {
"en": "University of Jyväskylä",
"fi": "Jyväskylän yliopisto",
"sv": "Jyväskylä universitet",
"und": "Jyväskylän yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01906",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "4712c574-515c-4499-b83a-c9317c7405b2",
"roles": [
"curator"
],
"person": {
"id": "65434134-6904-479e-a368-77b5fbba3ce3",
"name": "User support FIN-CLARIN",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "4f1668a4-d136-452d-9c53-619640e4ca6c",
"roles": [
"rights_holder"
],
"organization": {
"id": "f1a57e80-e3f3-4353-bd7d-67f252564fca",
"pref_label": {
"en": "The Matriculation Examination Board"
},
"homepage": {
"url": "https://www.ylioppilastutkinto.fi/fi/english"
},
"email": "<hidden>"
}
},
{
"id": "a742616b-352b-490d-9ef4-fe33d97116c9",
"roles": [
"publisher"
],
"organization": {
"id": "570ca63c-2128-42ee-ad9a-f29911bafa19",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "Finnish language essays / compositions written by Finnish-speaking students taking the matriculation examination in 1986. The corpus is available in Kielipankki - the Language Bank of Finland in Korp (https://korp.csc.fi/).\n\nCorpus access instruction: https://www.kielipankki.fi/support/corpus-location/ (in Finnish: https://www.kielipankki.fi/tuki/kayttooikeudet/) \n\nlog\n25.11.2018 link http://islrn.org/resources/596-037-998-620-1 removed\n\nInstructions on how to access Kielipankki corpora: https://www.kielipankki.fi/support/corpus-location/ (in Finnish: https://www.kielipankki.fi/tuki/aineiston-sijainti-kielipankissa/) \n\nImportant: when applying for the resource at https://lbr.csc.fi/ you are to provide, at the request of the IPR holder of the corpus (The Matriculation Examination Board of Finland), also information on your home address. Undergraduate students should provide their supervisor's email address as well. \n\nFor details on the license see http://urn.fi/urn:nbn:fi:lb-2016041801 (in Finnish: http://urn.fi/urn:nbn:fi:lb-2016041802)"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-20140730158",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "FinStud86 Corpus"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T13:03:15Z",
"dataset_versions": [
{
"id": "e5324440-ed23-4c52-b914-a04f5e51f814",
"title": {
"en": "FinStud86 Corpus"
},
"persistent_identifier": "urn:nbn:fi:lb-20140730158",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 15,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "a5feafcb-b10e-453a-8f41-2f96c6527274",
"access_rights": {
"id": "fc31e0be-f0ce-4e15-a423-c72a92446273",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-201806052",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "7441b7f9-2946-4eeb-9a15-aec04b3db05d",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "39b2af8b-53a5-4c74-82dc-60f7129bd7e7",
"name": "Hurskainen Arvi",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "4fa12b5e-2e67-45fd-9458-bfabff749e53",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "a80c3137-15c9-4569-9920-8c1b2943fb6c",
"roles": [
"curator"
],
"person": {
"id": "bda59a8e-dda2-4520-89a7-4b5dc6045b90",
"name": "User support at CSC - IT Center for Science Ltd. The Language Bank of Finland",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus is available for Download at Kielipankki - the Language Bank of Finland at http://urn.fi/urn:nbn:fi:lb-201803272\n\nThis is the downloadable version of Helsinki Corpus of Swahili 2.0 (HCS 2.0) Annotated Version, see http://urn.fi/urn:nbn:fi:lb-2016011301 for more information.\n\nThe Helsinki Corpus of Swahili 2.0 Annotated Version containing about 25 million words will be available in Kielipankki - the Language Bank of Finland in Download (https://korp.csc.fi/download) for academic use. This means that students and staff of universities can use the corpus by simply logging in with their university credentials. Alumni have the option to apply for access via https://lbr.csc.fi.\n\nAccess rights instructions: https:/ /www.kielipankki.fi/support/access (in Finnish: https://www.kielipankki.fi/tuki/kayttooikeudet/).\n\nInstructions on how to access Kielipankki corpora: https://www.kielipankki.fi/support/corpus-location/ (in Finnish: https://www.kielipankki.fi/tuki/aineiston-sijainti/).\n\nThe corpus contains various kinds of linguistic information attached to each token. The corpus was annotated using the Salama Tagger.\n\nPreparation of the material\n\nMost of the corpus material was retrieved from the Web. This method was used increasingly after texts in the Web became available. Only texts in news media and on open government pages were retrieved. Some types of texts, such as books, were scanned and proofread. Part of the oldest news material before the time of scanners in the 1980’ies was manually typed.\n\nThe corpus material has gone through a series of formatting and correction routines.\n\n1. Converting the text into ascii-format, required by the tagger. There is a wild variety of codes for describing diacritics in Web texts. These had to be formalized.\n2. Proofreading and correcting the text with a speller.\n3. Analyzing the proofread text for finding still remaining typos and possibly new words.\n4. Constructing a correction program that automatically corrects such typos that can be safely corrected. More than 8000 such mistake types were identified.\n5. New words found in corpus were added to the parser.\n6. Texts were corrected using the constructed correction program.\n7. Metadata in text files were formalized.\n8. Texts were converted into sentence-per-line format.\n9. Text within each file was randomly shuffled to mix the sentence order.\n\nThe result of these routines comprises the Helsinki Corpus of Swahili 2.0 Not Annotated Version.\n\nThe result of these routines was annotated with Salama Tagger, thus producing the Korp format of the corpus.\n\nMetadata were added to each file.\n\nStructure of the corpus\n\nHCS 2.0 contains the following types of material:\n\nOld material\n\n1. Books\n2. News\nNew material\n1. Bunge\n2. News\n\nOld material contains material before 2003. Much of this material is in Helsinki Corpus of Swahili 1.0. The big difference is, however, that while in the earlier corpus only sections of books were included, in the new corpus whole texts are included. The other difference is that while in the old corpus text sections are in the original order, in the new corpus sentences are randomly shuffled.\n\nMost of the new material consists of news texts from 2004-2015. The section ‘Bunge’ contains Hansards of the Tanzanian Parliament from the years 2004, 2005 and 2006. Metadata in the beginning of each file give more information. Also the names of the files give hints of the contents of the files.\n\nA word in the annotated corpus contains normally the following types of information:\n\n1. token\n2. stem\n3. part-of-speech\n4. morphological description\n5. gloss in English\n6. syntactic tag\n7. rest of verb description\n\nThe last point concerns only verbs.\n\nDetailed license information: See Documentation section below."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "3dc7924d-d652-468f-9ff5-67292f0b18ad",
"url": "http://lexvo.org/id/iso639-3/swa",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Swahili",
"fi": "Swahilin kieli",
"sv": "Swahili"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-201803271",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Helsinki Corpus of Swahili 2.0 (HCS 2.0) Downloadable Annotated Version",
"fi": "Helsinki Swahili -korpus 2.0 (HCS 2.0), ladattava annotoitu versio"
},
"created": "2022-11-17T00:00:00Z",
"modified": "2024-12-04T12:57:17Z",
"dataset_versions": [
{
"id": "a5feafcb-b10e-453a-8f41-2f96c6527274",
"title": {
"en": "Helsinki Corpus of Swahili 2.0 (HCS 2.0) Downloadable Annotated Version",
"fi": "Helsinki Swahili -korpus 2.0 (HCS 2.0), ladattava annotoitu versio"
},
"persistent_identifier": "urn:nbn:fi:lb-201803271",
"state": "published",
"created": "2022-11-17T00:00:00Z",
"version": 1
}
],
"published_revision": 13,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "c8596ad5-1975-4b50-9634-e1c5f5afd7fd",
"access_rights": {
"id": "fddb6819-0b18-4f7c-ad16-118d13ac5f28",
"license": [
{
"id": "edc3e7d1-0e14-490e-a7dd-6ace3dcb3673",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC0-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons CC0 1.0 Universal (CC0 1.0) Public Domain Dedication",
"fi": "Creative Commons Yleismaailmallinen (CC0 1.0) Public Domain -lausuma"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "5126385c-af7b-4aea-a390-cb9e29cb54da",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "ee193871-543c-414a-8831-cd5224a00021",
"name": "Mietta Lennes",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "b0114513-ca9e-43db-a4c3-a9bc30256483",
"roles": [
"creator"
],
"person": {
"id": "681a48e1-e619-4561-befb-3ee7bb2ffe6c",
"name": "Jussi Piitulainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "cefd1004-28f6-46be-a0d6-dcc749684c94",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "36d271d7-8d6a-44d2-b794-5cd1d40d0138",
"name": "Tero Aalto",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "fbbd6ea0-39c1-4af0-a485-165cadb76fa8",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "d41dacd2-a3bb-4cdf-bc9a-6f069d563c26",
"roles": [
"curator"
],
"person": {
"id": "9d355f04-67e0-4f39-b492-83542f9365f0",
"name": "User support at CSC - IT Center for Science Ltd. The Language Bank of Finland",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "06e825dd-9df8-4d1f-a6f7-573025013741",
"roles": [
"rights_holder"
],
"person": {
"id": "e2114598-c51b-4e9d-bb65-f6ee6baa55c8",
"name": "Jussi Piitulainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The resource, which is the Helsinki Korp version of the Route to A wing Corpus, is available in Kielipankki - the Language Bank of Finland at http://urn.fi/urn:nbn:fi:lb-2015050502\n\nFor more information see http://urn.fi/urn:nbn:fi:lb-2014101401"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2016042614",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "The Helsinki Korp Version of the Route to A wing Corpus",
"fi": "Reitti A-siipeen -korpuksen Helsinki-Korp-versio"
},
"created": "2023-04-05T00:00:00Z",
"modified": "2024-12-04T12:53:57Z",
"dataset_versions": [
{
"id": "c8596ad5-1975-4b50-9634-e1c5f5afd7fd",
"title": {
"en": "The Helsinki Korp Version of the Route to A wing Corpus",
"fi": "Reitti A-siipeen -korpuksen Helsinki-Korp-versio"
},
"persistent_identifier": "urn:nbn:fi:lb-2016042614",
"state": "published",
"created": "2023-04-05T00:00:00Z",
"version": 1
}
],
"published_revision": 14,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "d2f2386a-fc21-499d-bafc-9378346a39c1",
"access_rights": {
"id": "baf54dea-3271-4212-a474-e40bba6b5525",
"license": [
{
"id": "edc3e7d1-0e14-490e-a7dd-6ace3dcb3673",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC0-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons CC0 1.0 Universal (CC0 1.0) Public Domain Dedication",
"fi": "Creative Commons Yleismaailmallinen (CC0 1.0) Public Domain -lausuma"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "46a7f148-6725-4785-a406-f73176c89d53",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "2655eef4-bb6b-40d7-9689-dbc6c577e554",
"name": "Mietta Lennes",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "610ed2c8-0aab-4de3-89ac-080cae3fc254",
"roles": [
"creator"
],
"person": {
"id": "177756aa-56cd-4a1a-8bd1-278740d6ac2a",
"name": "Jussi Piitulainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "5a186eea-b4e1-42c1-9c55-177a48e9905a",
"roles": [
"creator",
"rights_holder"
],
"person": {
"id": "d690219d-938c-43a3-b7d1-e9536d234138",
"name": "Tero Aalto",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "7f1599bd-aaa6-4b8f-8068-a93daa619460",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "f2d1e04b-175b-4f83-9e4f-404536fec42c",
"roles": [
"curator"
],
"person": {
"id": "0067ec3f-8425-462d-8edb-3bb2a874f324",
"name": "User support at CSC - IT Center for Science Ltd. The Language Bank of Finland",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "d744a548-a01e-4485-a542-021e2a88c4ed",
"roles": [
"rights_holder"
],
"person": {
"id": "06f9c592-8156-4ba5-bfbc-4ce4430850a8",
"name": "Jussi Piitulainen",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "Until November 2020, this corpus was available via the LAT platform in Kielipankki - the Language Bank of Finland (see Access location).\n\nA downloadable version of the same content is available (see Relations). Further details about the most recent version are available on the info page of this corpus family (https://www.kielipankki.fi/aineistot/reittidemo/, in Finnish).",
"fi": "Tämä aineisto oli saatavilla Kielipankin LAT-alustan kautta marraskuuhun 2020 saakka (ks. Access location).\n\nAineistosta on saatavilla vastaavan sisältöinen ladattava versio (ks. Relations). Lisätietoja löytyy aineiston tietosivulta Kielipankissa (ks. https://www.kielipankki.fi/aineistot/reittidemo)"
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2016042613",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "The Helsinki LAT Version of the Route to A wing Corpus",
"fi": "Reitti A-siipeen -korpuksen Helsinki-LAT-versio"
},
"created": "2023-09-09T00:00:00Z",
"modified": "2024-12-04T12:53:53Z",
"dataset_versions": [
{
"id": "d2f2386a-fc21-499d-bafc-9378346a39c1",
"title": {
"en": "The Helsinki LAT Version of the Route to A wing Corpus",
"fi": "Reitti A-siipeen -korpuksen Helsinki-LAT-versio"
},
"persistent_identifier": "urn:nbn:fi:lb-2016042613",
"state": "published",
"created": "2023-09-09T00:00:00Z",
"version": 1
}
],
"published_revision": 14,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "143c69e4-9347-45bb-926d-f16faf47768d",
"access_rights": {
"id": "1bf9d675-1898-4a30-8561-9bae8f3a4655",
"license": [
{
"id": "fc8a7008-cf5e-4df1-9e05-0145d445c80e",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-20150304134",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinRES-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN RES (Restricted) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "41b4ff93-e15e-4829-8553-49e4ef079d69",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/other",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restricted access due to other reasons",
"fi": "Saatavuutta rajoitettu muulla perusteella",
"sv": "Begränsad åtkomst av övriga skäl"
}
}
]
},
"actors": [
{
"id": "d7c057cc-0076-4cee-aa60-354a285586c3",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a",
"pref_label": {
"en": "University of Jyväskylä",
"fi": "Jyväskylän yliopisto",
"sv": "Jyväskylä universitet",
"und": "Jyväskylän yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01906",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "b5317b81-5dd1-4cb0-8df6-17aeed0c4af6",
"roles": [
"curator"
],
"person": {
"id": "0d701595-f9da-4a11-a379-70149233765b",
"name": "User support at CSC - IT Center for Science Ltd. The Language Bank of Finland",
"email": "<hidden>"
},
"organization": {
"id": "477dfdb6-563e-41d9-badc-ec3975f79256",
"pref_label": {
"en": "CSC – IT Center for Science",
"fi": "CSC - Tieteen tietotekniikan keskus Oy",
"sv": "CSC – IT Center for Science",
"und": "CSC - Tieteen tietotekniikan keskus Oy"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/09206320",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "aaf593ee-68c1-45af-bb83-8f3f97709cc7",
"roles": [
"curator"
],
"person": {
"id": "ab01fe2b-0d8a-4187-a9e1-ce153b951228",
"name": "Terho Joutsen",
"email": "<hidden>"
},
"organization": {
"id": "bdd6cb24-71fe-40e0-9ba0-bfb1ea32b50a",
"pref_label": {
"en": "University of Jyväskylä",
"fi": "Jyväskylän yliopisto",
"sv": "Jyväskylä universitet",
"und": "Jyväskylän yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01906",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "a4c40880-7c92-4b66-b5d3-e499c4d771ac",
"roles": [
"publisher"
],
"organization": {
"id": "eac20fd9-c416-494f-a06e-189d8b90c93c",
"pref_label": {
"en": "Multiple publishers, check distribution rights holders in original metadata by following its persistent identifier"
}
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus is available in Kielipankki - the Language Bank of Finland (puhti.csc.fi, access rights instructions: https://www.kielipankki.fi/support/access/) \n\nLicence: https://www.kielipankki.fi/lic/kra/\n\nA digitized corpus for the study of the lexis and syntax of Middle French and for text editions.\n\nThe corpus consists of 14 documents and 430 000 words. The corpus contains prose, novels, plays and lyrical poetry. It can be used to study the Middle French vocabulary and syntax. \n\nLicense information: http://urn.fi/urn:nbn:fi:lb-20150304134\n\nMore information on the corpus:\nhttp://urn.fi/urn:nbn:fi:lb-201406034\n\nThe purpose of the resource use must be outlined in a research plan."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "0974b041-177a-48b6-b3af-0f68e212d27e",
"url": "http://lexvo.org/id/iso639-3/frm",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Middle French",
"fi": "keskiranska",
"sv": "medelfranska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-201403264",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Jyväskylä Corpus of Middle French",
"fi": "Keskiranskan korpus"
},
"created": "2023-04-07T00:00:00Z",
"modified": "2024-12-04T12:51:48Z",
"dataset_versions": [
{
"id": "143c69e4-9347-45bb-926d-f16faf47768d",
"title": {
"en": "Jyväskylä Corpus of Middle French",
"fi": "Keskiranskan korpus"
},
"persistent_identifier": "urn:nbn:fi:lb-201403264",
"state": "published",
"created": "2023-04-07T00:00:00Z",
"version": 1
}
],
"published_revision": 15,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "a0c049db-1b5a-43d1-a9ec-5a1a156c0f7e",
"access_rights": {
"id": "2f5c4bcc-b276-4529-b04b-09c386f16101",
"license": [
{
"id": "64b8be74-3aac-4b1d-8b0a-1b8d3c15a9e9",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2024070701",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/CC-BY-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "Creative Commons Attribution 1.0 Generic (CC BY 1.0)",
"fi": "Creative Commons Nimeä 1.0 Yleinen (CC BY 1.0)"
}
}
],
"access_type": {
"id": "b41462f7-00bf-4e50-935b-2bf1184453a7",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/open",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Open",
"fi": "Avoin"
}
},
"restriction_grounds": []
},
"actors": [
{
"id": "a7cbe292-e351-4b99-be65-4b140f9f7c73",
"roles": [
"creator",
"curator",
"rights_holder"
],
"person": {
"id": "5b3c903e-70b9-40cd-b927-8e15ec489415",
"name": "Lotta Aunio",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "319283d1-cf45-4835-98df-cf2129a082f7",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "The corpus will be available in the Language Bank of Finland via Korp.\n\nThis corpus of spoken Ha language consists of transcripts of various types of natural speech (stories, discussions and elicited materials) collected in the towns of Kibondo, Kasulu and Kigoma and nearby regions in Tanzania during the years 1997, 2000 and 2003. The original transcripts have been pseudonymized.\n\nHa language (ISO 639-3: haq; Great Lakes Bantu language JD66; alternative names Igiha, Giha, Kiha) is spoken in Western Tanzania in the Kigoma region. It is closely related to, for example, Rundi of Burundi and Kinyarwanda of Rwanda. Ha is one of biggest languages in Tanzania with approximately 1,2 million speakers.\n\nThe collection and analysis of the corpus data is described in the following publication:\nHarjula, Lotta 2004. The Ha Language of Tanzania: Grammar, Texts, and Vocabulary. East African Languages and Dialects 13. Cologne: Köppe. ISBN 978-3-89645-027-2.",
"fi": "Aineisto on tulossa saataville Kielipankin Korp-palvelun kautta.\n\nAineisto sisältää eri tyyppisten puhutun han kielen näytteiden (tarinat, keskustelut ja elisitoidut lauseet) tekstimuotoisia litteraatteja. Näytteet on kerätty Kibondon, Kasulun ja Kigoman kaupungeissa ja niiden ympäristössä Länsi-Tansaniassa vuosina 199, 2000 ja 2003. Alkuperäiset litteraatit on peudonymisoitu.\n\nHan kieltä (ISO 639-3: haq; Suurten järvien bantukieli JD66; vaihtoehtoiset nimet igiha, giha, kiha) puhutaan Länsi-Tansaniassa Kigoman läänissä. Se on läheistä sukua esimerkiksi Burundissa puhuttavalle rundin kielelle ja Ruandan kinyaruandalle. Ha on yksi Tansanian suurimmista kielistä: sitä puhuu noin 1,2 miljoonaa ihmistä.\n\nAineiston keruu ja analyysi on tarkemmin kuvattu seuraavassa han kielioppia ja sanastoa käsittelevässä teoksessa:\nHarjula, Lotta, 2004. The Ha Language of Tanzania: Grammar, Texts, and Vocabulary. East African Languages and Dialects 13. Köln: Köppe. ISBN 978-3-89645-027-2."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "5dd35420-578c-48c1-996a-90c569b3ffd3",
"url": "http://lexvo.org/id/iso639-3/haq",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Ha"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2017022101",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Ha Language Corpus, Helsinki Korp Version",
"fi": "Ha-kieliaineiston Helsinki-Korp-versio"
},
"created": "2023-04-05T00:00:00Z",
"modified": "2024-07-10T08:40:29Z",
"dataset_versions": [
{
"id": "a0c049db-1b5a-43d1-a9ec-5a1a156c0f7e",
"title": {
"en": "Ha Language Corpus, Helsinki Korp Version",
"fi": "Ha-kieliaineiston Helsinki-Korp-versio"
},
"persistent_identifier": "urn:nbn:fi:lb-2017022101",
"state": "published",
"created": "2023-04-05T00:00:00Z",
"version": 1
}
],
"published_revision": 14,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "29f8621f-7fd4-4051-8eb8-8cde86352606",
"access_rights": {
"id": "9e97f9d9-c7f0-4f53-8645-415149ec7069",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2019121001",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "1bd055ec-96c7-4ff4-8a44-8b1dee559dd1",
"roles": [
"creator",
"curator"
],
"person": {
"id": "c46b0104-a12b-45b2-9686-155cd63a972a",
"name": "Anna Dmitrieva",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "11265d13-1869-45a2-b77d-30949011f810",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "0dcc95ab-5795-4014-af70-29d526b0b396",
"pref_label": {
"en": "Finnish Broadcasting Company (Yle)",
"fi": "Yleisradio Oy"
},
"homepage": {
"url": "https://yle.fi/"
},
"email": "<hidden>"
}
},
{
"id": "9770abe1-d6ae-4fc9-b5ca-71c5d039ee41",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "This resource will be available via Korp in Kielipankki – the Language Bank of Finland.\n\nThis is a parallel corpus created of the Yle news articles from 2014-2020 by aligning the standard Finnish versions with the easy-language versions. The dataset, created by Anna Dmitrieva and available in CSV format, is aligned on the sentence level. It is based on the two parallel document-level datasets of Yle News articles available on Kielipankki (http://urn.fi/urn:nbn:fi:lb-2022111625 and http://urn.fi/urn:nbn:fi:lb-2024011701) The dataset spans the period from September 2014 to December 2020.\n\nThis dataset is comprised of the following parts:\n1) Sentence alignments: parallel documents from regular and Easy Finnish Yle news articles aligned sentence-by-sentence. Only the \"positive\" documents were taken from the 2019-2020 dataset (http://urn.fi/urn:nbn:fi:lb-2022111625) All but 50 documents were aligned automatically with Vecalign (https://github.com/thompsonb/vecalign) using LASER embeddings (https://github.com/facebookresearch/LASER) Each document has the following columns:\n1.1) pair_id: an id comprised of three parts divided by a double underscore: the id of the regular document, the id of the Easy Finnish document (with a singular underscore), and the sentence pair number.\n1.2) regular_string: a sentence from the regular Finnish article.\n1.3) selko_string: a corresponding sentence from the Easy Finnish article.\n1.4) score: the confidence score given by Vecalign. The lower the score, the more similar the sentences. The \"good\" pairs are estimated to have a score below or equal to 0.65; however, the score is not definitive proof of whether the sentences in the pair truly match in meaning. The zero score is assigned when a sentence has no pair. The scores for all non-zero sentence pairs in manually aligned documents are set to 0.(3).\n2) Golden sentence alignments: 50 documents aligned manually by a human assessor (text). Also available in the ladder format (indexes)."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2024031301",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, Korp",
"fi": "Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, Korp"
},
"created": "2024-03-27T00:00:00Z",
"modified": "2024-06-19T08:32:26Z",
"dataset_versions": [
{
"id": "29f8621f-7fd4-4051-8eb8-8cde86352606",
"title": {
"en": "Parallel Sentence Aligned Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2020, Korp",
"fi": "Lausetasolla kohdistettu suomi–selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2020, Korp"
},
"persistent_identifier": "urn:nbn:fi:lb-2024031301",
"state": "published",
"created": "2024-03-27T00:00:00Z",
"version": 1
}
],
"published_revision": 12,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
},
{
"id": "c39baf38-167a-4924-9088-42b098e47f5e",
"access_rights": {
"id": "f2444709-3619-45b5-aaec-b77045662ee0",
"license": [
{
"id": "cef12353-9b39-4c92-8a0c-8de977ac8d28",
"custom_url": "http://urn.fi/urn:nbn:fi:lb-2022050901",
"url": "http://uri.suomi.fi/codelist/fairdata/license/code/ClarinACA+NC-1.0",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/license",
"pref_label": {
"en": "CLARIN ACA+NC (Academic, Non-Commercial) End-User License 1.0"
}
}
],
"access_type": {
"id": "6311561d-0b53-460b-9fb9-1852ce0761eb",
"url": "http://uri.suomi.fi/codelist/fairdata/access_type/code/restricted",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/access_type",
"pref_label": {
"en": "Restricted use",
"fi": "Saatavuutta rajoitettu"
}
},
"restriction_grounds": [
{
"id": "d0da98cd-9cd2-4352-b12a-3e3efcb585fd",
"url": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds/code/research",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/restriction_grounds",
"pref_label": {
"en": "Restriced access for research based on contract",
"fi": "Saatavuutta rajoitettu sopimuksen perusteella vain tutkimuskäyttöön",
"sv": "Begränsad åtkomst på bas av kontrakt ändast för forskningsändamål"
}
}
]
},
"actors": [
{
"id": "a2c52220-3674-4dc9-9506-3a5673fe79e9",
"roles": [
"creator",
"curator"
],
"person": {
"id": "96f9aea5-f8c2-4041-8586-1b0766052fbf",
"name": "Anna Dmitrieva",
"email": "<hidden>"
},
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
},
{
"id": "2100680b-2823-41fa-b4ac-98edba39627a",
"roles": [
"creator",
"rights_holder"
],
"organization": {
"id": "f4e023be-53b8-4eb7-b502-50958280aa5c",
"pref_label": {
"en": "Finnish Broadcasting Company (Yle)",
"fi": "Yleisradio Oy"
},
"homepage": {
"url": "https://yle.fi/"
},
"email": "<hidden>"
}
},
{
"id": "863ca0b1-bd7a-4fe9-9c7b-c6e24dc613e2",
"roles": [
"publisher"
],
"organization": {
"id": "a5f4935c-4c0e-44f6-a7d6-71b946913649",
"pref_label": {
"en": "University of Helsinki",
"fi": "Helsingin yliopisto",
"sv": "Helsingfors universitet",
"und": "Helsingin yliopisto"
},
"url": "http://uri.suomi.fi/codelist/fairdata/organization/code/01901",
"in_scheme": "http://uri.suomi.fi/codelist/fairdata/organization"
}
}
],
"cumulative_state": 0,
"data_catalog": "urn:nbn:fi:att:data-catalog-harvest-kielipankki",
"description": {
"en": "This resource is available for download in Kielipankki – the Language Bank of Finland.\n\nThis is a parallel corpus created of the Yle news articles from 2014-2018 by aligning the standard Finnish versions with the easy-language versions. The dataset, created by Anna Dmitrieva and available in CSV format, is aligned on the document level. The news articles were obtained from the datasets available via Kielipankki (http://urn.fi/urn:nbn:fi:lb-2017070501 and http://urn.fi/urn:nbn:fi:lb-2019050901).\n\nThis dataset extends the previously published Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2019-2020 (http://urn.fi/urn:nbn:fi:lb-2022111625) Please note that this dataset has not been assessed by a human expert. The articles have been aligned automatically with the Vecalign document alignment algorithm (https://github.com/thompsonb/vecalign) without candidate rescoring, using LASER embeddings (https://github.com/facebookresearch/LASER).\n\nDescription of all columns in the dataset:\n-index_in_selko: This index consists of two parts divided by an underscore. The first (longer) part identifies the entire Easy Finnish article from the original dataset. The second (shorter) part is the number of the paragraph. Since the Yle Selkosuomi articles usually consist of multiple paragraphs, each paragraph describing a separate piece of news, we represent each paragraph as an individual little article in our dataset. Paragraph numbering starts with 0.\n- index_in_regular: The identifier of the regular Finnish article taken from the original dataset.\n- selko_text: A piece of news in Easy Finnish.\n- regular_text: A corresponding piece of news in regular Finnish.\n- distance: The cosine distance between the document vectors. The lower the distance, the more similar the documents are."
},
"field_of_science": [
{
"id": "f7ee5ba6-f6af-48d0-bb0f-ea26851256d2",
"url": "http://www.yso.fi/onto/okm-tieteenala/ta6121",
"in_scheme": "http://www.yso.fi/onto/okm-tieteenala/conceptscheme",
"pref_label": {
"en": "Languages",
"fi": "Kielitieteet",
"sv": "Språkvetenskaper"
}
}
],
"infrastructure": [],
"keyword": [],
"language": [
{
"id": "b0c7eada-5b22-48b8-86c2-16e996ca2681",
"url": "http://lexvo.org/id/iso639-3/fin",
"in_scheme": "http://lexvo.org/id/",
"pref_label": {
"en": "Finnish",
"fi": "suomi",
"sv": "finska"
}
}
],
"metadata_owner": {
"id": "003e43bb-cfd5-43a5-92c8-1a6cbec7f76c",
"organization": "service_kielipankki"
},
"other_identifiers": [],
"persistent_identifier": "urn:nbn:fi:lb-2024011701",
"pid_generated_by_fairdata": false,
"projects": [],
"provenance": [],
"relation": [],
"remote_resources": [],
"spatial": [],
"state": "published",
"temporal": [],
"theme": [],
"title": {
"en": "Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2018, source",
"fi": "Suomi-selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2018, lähdeaineisto"
},
"created": "2024-02-02T00:00:00Z",
"modified": "2024-06-19T08:31:00Z",
"dataset_versions": [
{
"id": "c39baf38-167a-4924-9088-42b098e47f5e",
"title": {
"en": "Parallel Corpus of Finnish and Easy-to-read Finnish from the Yle News Archive 2014-2018, source",
"fi": "Suomi-selkosuomi-rinnakkaiskorpus Ylen suomenkielisestä uutisarkistosta 2014-2018, lähdeaineisto"
},
"persistent_identifier": "urn:nbn:fi:lb-2024011701",
"state": "published",
"created": "2024-02-02T00:00:00Z",
"version": 1
}
],
"published_revision": 12,
"version": 1,
"api_version": 3,
"metadata_repository": "Fairdata"
}
]
}
