{"id":1330,"date":"2023-11-10T16:06:34","date_gmt":"2023-11-10T16:06:34","guid":{"rendered":"https:\/\/fyribils.maltokni.fo\/?post_type=product&#038;p=1330"},"modified":"2023-11-10T16:31:39","modified_gmt":"2023-11-10T16:31:39","slug":"wili-2018-wikipedia-language-identification-database","status":"publish","type":"product","link":"https:\/\/mtd.setur.fo\/en\/resource\/wili-2018-wikipedia-language-identification-database\/","title":{"rendered":"WiLI-2018: Wikipedia Language Identification Database"},"content":{"rendered":"<p>WiLI-2018, the Wikipedia language identification benchmark dataset, contains 235000 paragraphs of 235 languages. The dataset is balanced, and a train-test split is provided.<\/p>\n<p>Download page: <a href=\"https:\/\/zenodo.org\/records\/841984\" target=\"_blank\" rel=\"noopener\">https:\/\/zenodo.org\/records\/841984<\/a><br \/>\nHugging Face Dataset: <a href=\"https:\/\/huggingface.co\/datasets\/wili_2018\" target=\"_blank\" rel=\"noopener\">https:\/\/huggingface.co\/datasets\/wili_2018<\/a><br \/>\nArticle: <a href=\"https:\/\/arxiv.org\/pdf\/1801.07779.pdf\" target=\"_blank\" rel=\"noopener\">https:\/\/arxiv.org\/pdf\/1801.07779.pdf<\/a><br \/>\nRelease: 2018<br \/>\nContact: <a href=\"mailto:info@martin-thoma.de\">info@martin-thoma.de<\/a><\/p>","protected":false},"excerpt":{"rendered":"<p>This contains 1,000 paragraphs in Faroese (and the same amount in all the other 234 languages). This means that there are 500 paragraphs in the training set and another 500 paragraphs in the test set. You can download the files for all 235 languages below.<\/p>","protected":false},"featured_media":1325,"template":"","meta":{"_uag_custom_page_level_css":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_wpas_customize_per_network":false},"product_brand":[],"product_cat":[18],"product_tag":[],"class_list":["post-1330","product","type-product","status-publish","has-post-thumbnail","product_cat-text","pa_format-txt","pa_language-faroese","pa_language-other-languages","pa_license-odbl","pa_publisher-martin-thoma","pa_uses-language-identification","desktop-align-left","tablet-align-left","mobile-align-left","first","instock","shipping-taxable","product-type-external"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mtd.setur.fo\/en\/resource\/wili-2018-wikipedia-language-identification-database\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin\" \/>\n<meta property=\"og:description\" content=\"This contains 1,000 paragraphs in Faroese (and the same amount in all the other 234 languages). This means that there are 500 paragraphs in the training set and another 500 paragraphs in the test set. You can download the files for all 235 languages below.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mtd.setur.fo\/en\/resource\/wili-2018-wikipedia-language-identification-database\/\" \/>\n<meta property=\"og:site_name\" content=\"M\u00e1lt\u00f8knidepilin\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-10T16:31:39+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1\" \/>\n\t<meta property=\"og:image:width\" content=\"512\" \/>\n\t<meta property=\"og:image:height\" content=\"512\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/\",\"url\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/\",\"name\":\"WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i0.wp.com\\\/mtd.setur.fo\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1\",\"datePublished\":\"2023-11-10T16:06:34+00:00\",\"dateModified\":\"2023-11-10T16:31:39+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/#primaryimage\",\"url\":\"https:\\\/\\\/i0.wp.com\\\/mtd.setur.fo\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1\",\"contentUrl\":\"https:\\\/\\\/i0.wp.com\\\/mtd.setur.fo\\\/wp-content\\\/uploads\\\/2023\\\/11\\\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1\",\"width\":512,\"height\":512},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/resource\\\/wili-2018-wikipedia-language-identification-database\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mtd.setur.fo\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Tilfeingi\",\"item\":\"https:\\\/\\\/mtd.setur.fo\\\/tilfeingi\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"WiLI-2018: Wikipedia Language Identification Database\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#website\",\"url\":\"https:\\\/\\\/mtd.setur.fo\\\/\",\"name\":\"M\u00e1lt\u00f8knidepilin\",\"description\":\"M\u00e1lt\u00f8knidepilin\",\"publisher\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mtd.setur.fo\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#organization\",\"name\":\"M\u00e1lt\u00f8knidepilin\",\"url\":\"https:\\\/\\\/mtd.setur.fo\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i0.wp.com\\\/mtd.setur.fo\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/cropped-gront_MTD_FF_fo_horisont-2.png?fit=550%2C110&ssl=1\",\"contentUrl\":\"https:\\\/\\\/i0.wp.com\\\/mtd.setur.fo\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/cropped-gront_MTD_FF_fo_horisont-2.png?fit=550%2C110&ssl=1\",\"width\":550,\"height\":110,\"caption\":\"M\u00e1lt\u00f8knidepilin\"},\"image\":{\"@id\":\"https:\\\/\\\/mtd.setur.fo\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mtd.setur.fo\/en\/resource\/wili-2018-wikipedia-language-identification-database\/","og_locale":"en_GB","og_type":"article","og_title":"WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin","og_description":"This contains 1,000 paragraphs in Faroese (and the same amount in all the other 234 languages). This means that there are 500 paragraphs in the training set and another 500 paragraphs in the test set. You can download the files for all 235 languages below.","og_url":"https:\/\/mtd.setur.fo\/en\/resource\/wili-2018-wikipedia-language-identification-database\/","og_site_name":"M\u00e1lt\u00f8knidepilin","article_modified_time":"2023-11-10T16:31:39+00:00","og_image":[{"width":512,"height":512,"url":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Estimated reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/","url":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/","name":"WiLI-2018: Wikipedia Language Identification Database - M\u00e1lt\u00f8knidepilin","isPartOf":{"@id":"https:\/\/mtd.setur.fo\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/#primaryimage"},"image":{"@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/#primaryimage"},"thumbnailUrl":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1","datePublished":"2023-11-10T16:06:34+00:00","dateModified":"2023-11-10T16:31:39+00:00","breadcrumb":{"@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/#primaryimage","url":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1","contentUrl":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1","width":512,"height":512},{"@type":"BreadcrumbList","@id":"https:\/\/mtd.setur.fo\/resource\/wili-2018-wikipedia-language-identification-database\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mtd.setur.fo\/"},{"@type":"ListItem","position":2,"name":"Tilfeingi","item":"https:\/\/mtd.setur.fo\/tilfeingi\/"},{"@type":"ListItem","position":3,"name":"WiLI-2018: Wikipedia Language Identification Database"}]},{"@type":"WebSite","@id":"https:\/\/mtd.setur.fo\/#website","url":"https:\/\/mtd.setur.fo\/","name":"Centre for Language Technology","description":"Centre for Language Technology","publisher":{"@id":"https:\/\/mtd.setur.fo\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mtd.setur.fo\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/mtd.setur.fo\/#organization","name":"Centre for Language Technology","url":"https:\/\/mtd.setur.fo\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/mtd.setur.fo\/#\/schema\/logo\/image\/","url":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2024\/02\/cropped-gront_MTD_FF_fo_horisont-2.png?fit=550%2C110&ssl=1","contentUrl":"https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2024\/02\/cropped-gront_MTD_FF_fo_horisont-2.png?fit=550%2C110&ssl=1","width":550,"height":110,"caption":"M\u00e1lt\u00f8knidepilin"},"image":{"@id":"https:\/\/mtd.setur.fo\/#\/schema\/logo\/image\/"}}]}},"jetpack_publicize_connections":[],"uagb_featured_image_src":{"full":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,false],"thumbnail":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=150%2C150&ssl=1",150,150,true],"medium":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=300%2C300&ssl=1",300,300,true],"medium_large":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"large":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"1536x1536":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"2048x2048":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"trp-custom-language-flag":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=12%2C12&ssl=1",12,12,true],"newspack-article-block-landscape-large":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-portrait-large":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-square-large":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-landscape-medium":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-portrait-medium":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-square-medium":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-landscape-intermediate":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C450&ssl=1",512,450,true],"newspack-article-block-portrait-intermediate":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=450%2C512&ssl=1",450,512,true],"newspack-article-block-square-intermediate":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=512%2C512&ssl=1",512,512,true],"newspack-article-block-landscape-small":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=400%2C300&ssl=1",400,300,true],"newspack-article-block-portrait-small":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=300%2C400&ssl=1",300,400,true],"newspack-article-block-square-small":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=400%2C400&ssl=1",400,400,true],"newspack-article-block-landscape-tiny":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=200%2C150&ssl=1",200,150,true],"newspack-article-block-portrait-tiny":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=150%2C200&ssl=1",150,200,true],"newspack-article-block-square-tiny":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=200%2C200&ssl=1",200,200,true],"newspack-article-block-uncropped":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"mailpoet_newsletter_max":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"woocommerce_thumbnail":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=300%2C300&ssl=1",300,300,true],"woocommerce_single":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?fit=512%2C512&ssl=1",512,512,true],"woocommerce_gallery_thumbnail":["https:\/\/i0.wp.com\/mtd.setur.fo\/wp-content\/uploads\/2023\/11\/wikipedia_logo_icon_169796.png?resize=100%2C100&ssl=1",100,100,true]},"uagb_author_info":{"display_name":"Admin","author_link":"https:\/\/mtd.setur.fo\/en\/author\/"},"uagb_comment_info":0,"uagb_excerpt":"This contains 1,000 paragraphs in Faroese (and the same amount in all the other 234 languages). This means that there are 500 paragraphs in the training set and another 500 paragraphs in the test set. You can download the files for all 235 languages below.","jetpack_likes_enabled":true,"jetpack_sharing_enabled":true,"jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/product\/1330","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/types\/product"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/media\/1325"}],"wp:attachment":[{"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/media?parent=1330"}],"wp:term":[{"taxonomy":"product_brand","embeddable":true,"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/product_brand?post=1330"},{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/product_cat?post=1330"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/mtd.setur.fo\/en\/wp-json\/wp\/v2\/product_tag?post=1330"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}