{"url":"/dataset/tatoeba","name":"Tatoeba","full_name":"Tatoeba","description_markdown":"Tatoeba is a free collection of example sentences with translations geared towards foreign language learners. It is available in more than 400 languages. Its name comes from the Japanese phrase “tatoeba” (例えば), meaning “for example”. It is written and maintained by a community of volunteers through a model of open collaboration. Individual contributors are known as Tatoebans.","description_withheld":null,"homepage":"https://tatoeba.org","introduced_date":"2018-12-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/massively-multilingual-sentence-embeddings","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","first_author":"Mikel Artetxe","url":null},"license":{"name":"CC–BY 2.0 FR","url":"https://creativecommons.org/licenses/by/2.0/fr/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"},{"name":"Translation deu-eng","url":"/task/translation-deu-eng","datasets_with_task":"/datasets/task/translation-deu-eng"},{"name":"Translation eng-deu","url":"/task/translation-eng-deu","datasets_with_task":"/datasets/task/translation-eng-deu"},{"name":"Translation spa-eng","url":"/task/translation-spa-eng","datasets_with_task":"/datasets/task/translation-spa-eng"},{"name":"Translation tur-eng","url":"/task/translation-tur-eng","datasets_with_task":"/datasets/task/translation-tur-eng"},{"name":"Translation afr-deu","url":"/task/translation-afr-deu-1","datasets_with_task":"/datasets/task/translation-afr-deu-1"},{"name":"Translation afr-eng","url":"/task/translation-afr-eng","datasets_with_task":"/datasets/task/translation-afr-eng"},{"name":"Translation deu-afr","url":"/task/translation-deu-afr","datasets_with_task":"/datasets/task/translation-deu-afr"},{"name":"Translation eng-afr","url":"/task/translation-eng-afr","datasets_with_task":"/datasets/task/translation-eng-afr"},{"name":"Translation eng-nld","url":"/task/translation-eng-nld","datasets_with_task":"/datasets/task/translation-eng-nld"},{"name":"Translation nld-eng","url":"/task/translation-nld-eng","datasets_with_task":"/datasets/task/translation-nld-eng"},{"name":"Translation cat-eng","url":"/task/translation-cat-eng","datasets_with_task":"/datasets/task/translation-cat-eng"},{"name":"Translation afr-nld","url":"/task/translation-afr-nld","datasets_with_task":"/datasets/task/translation-afr-nld"},{"name":"Translation deu-nld","url":"/task/translation-deu-nld","datasets_with_task":"/datasets/task/translation-deu-nld"},{"name":"Translation ltz-deu","url":"/task/translation-ltz-deu","datasets_with_task":"/datasets/task/translation-ltz-deu"},{"name":"Translation ltz-eng","url":"/task/translation-ltz-eng","datasets_with_task":"/datasets/task/translation-ltz-eng"},{"name":"Translation ltz-nld","url":"/task/translation-ltz-nld","datasets_with_task":"/datasets/task/translation-ltz-nld"},{"name":"Translation nld-afr","url":"/task/translation-nld-afr","datasets_with_task":"/datasets/task/translation-nld-afr"},{"name":"Translation nld-deu","url":"/task/translation-nld-deu","datasets_with_task":"/datasets/task/translation-nld-deu"},{"name":"Translation fry-eng","url":"/task/translation-fry-eng","datasets_with_task":"/datasets/task/translation-fry-eng"},{"name":"Translation fry-nld","url":"/task/translation-fry-nld","datasets_with_task":"/datasets/task/translation-fry-nld"},{"name":"Translation hrx-deu","url":"/task/translation-hrx-deu","datasets_with_task":"/datasets/task/translation-hrx-deu"},{"name":"Translation hrx-eng","url":"/task/translation-hrx-eng","datasets_with_task":"/datasets/task/translation-hrx-eng"},{"name":"Translation nds-deu","url":"/task/translation-nds-deu","datasets_with_task":"/datasets/task/translation-nds-deu"},{"name":"Translation nds-eng","url":"/task/translation-nds-eng","datasets_with_task":"/datasets/task/translation-nds-eng"},{"name":"Translation nds-nld","url":"/task/translation-nds-nld","datasets_with_task":"/datasets/task/translation-nds-nld"},{"name":"Translation nld-fry","url":"/task/translation-nld-fry","datasets_with_task":"/datasets/task/translation-nld-fry"},{"name":"Translation nld-nds","url":"/task/translation-nld-nds","datasets_with_task":"/datasets/task/translation-nld-nds"},{"name":"Sentence Embedding","url":"/task/sentence-embedding","datasets_with_task":"/datasets/task/sentence-embedding"},{"name":"Translation gos-deu","url":"/task/translation-gos-deu","datasets_with_task":"/datasets/task/translation-gos-deu"},{"name":"Translation gos-eng","url":"/task/translation-gos-eng","datasets_with_task":"/datasets/task/translation-gos-eng"},{"name":"Translation rus-eng","url":"/task/translation-rus-eng","datasets_with_task":"/datasets/task/translation-rus-eng"},{"name":"Translation rus-deu","url":"/task/translation-rus-deu","datasets_with_task":"/datasets/task/translation-rus-deu"},{"name":"Translation bel-deu","url":"/task/translation-bel-deu","datasets_with_task":"/datasets/task/translation-bel-deu"},{"name":"Translation bel-fra","url":"/task/translation-bel-fra","datasets_with_task":"/datasets/task/translation-bel-fra"},{"name":"Translation rus-por","url":"/task/translation-rus-por","datasets_with_task":"/datasets/task/translation-rus-por"},{"name":"Translation rus-spa","url":"/task/translation-rus-spa","datasets_with_task":"/datasets/task/translation-rus-spa"},{"name":"Translation bel-spa","url":"/task/translation-bel-spa","datasets_with_task":"/datasets/task/translation-bel-spa"},{"name":"Translation eng-cat","url":"/task/translation-eng-cat","datasets_with_task":"/datasets/task/translation-eng-cat"},{"name":"Translation eng-spa","url":"/task/translation-eng-spa","datasets_with_task":"/datasets/task/translation-eng-spa"},{"name":"Translation eng-fra","url":"/task/translation-eng-fra","datasets_with_task":"/datasets/task/translation-eng-fra"},{"name":"Translation eng-por","url":"/task/translation-eng-por","datasets_with_task":"/datasets/task/translation-eng-por"},{"name":"Translation eng-tur","url":"/task/translation-eng-tur","datasets_with_task":"/datasets/task/translation-eng-tur"},{"name":"Translation ara-eng","url":"/task/translation-ara-eng","datasets_with_task":"/datasets/task/translation-ara-eng"},{"name":"Translation bul-eng","url":"/task/translation-bul-eng","datasets_with_task":"/datasets/task/translation-bul-eng"},{"name":"Translation cym-eng","url":"/task/translation-cym-eng","datasets_with_task":"/datasets/task/translation-cym-eng"},{"name":"Translation gle-eng","url":"/task/translation-gle-eng","datasets_with_task":"/datasets/task/translation-gle-eng"},{"name":"Translation ces-eng","url":"/task/translation-ces-eng","datasets_with_task":"/datasets/task/translation-ces-eng"},{"name":"Translation ell-eng","url":"/task/translation-ell-eng","datasets_with_task":"/datasets/task/translation-ell-eng"},{"name":"Translation est-eng","url":"/task/translation-est-eng","datasets_with_task":"/datasets/task/translation-est-eng"},{"name":"Translation fra-eng","url":"/task/translation-fra-eng","datasets_with_task":"/datasets/task/translation-fra-eng"},{"name":"Translation dan-eng","url":"/task/translation-dan-eng","datasets_with_task":"/datasets/task/translation-dan-eng"},{"name":"Translation isl-eng","url":"/task/translation-isl-eng","datasets_with_task":"/datasets/task/translation-isl-eng"},{"name":"Translation fao-eng","url":"/task/translation-fao-eng","datasets_with_task":"/datasets/task/translation-fao-eng"},{"name":"Translation hrv-eng","url":"/task/translation-hrv-eng","datasets_with_task":"/datasets/task/translation-hrv-eng"},{"name":"Translation bos_Latn-eng","url":"/task/translation-bos-latn-eng","datasets_with_task":"/datasets/task/translation-bos-latn-eng"},{"name":"Translation hbs-eng","url":"/task/translation-hbs-eng","datasets_with_task":"/datasets/task/translation-hbs-eng"},{"name":"Translation heb-eng","url":"/task/translation-heb-eng","datasets_with_task":"/datasets/task/translation-heb-eng"},{"name":"Translation hun-eng","url":"/task/translation-hun-eng","datasets_with_task":"/datasets/task/translation-hun-eng"},{"name":"Translation lav-eng","url":"/task/translation-lav-eng","datasets_with_task":"/datasets/task/translation-lav-eng"},{"name":"Translation slv-eng","url":"/task/translation-slv-eng","datasets_with_task":"/datasets/task/translation-slv-eng"},{"name":"Translation pol-eng","url":"/task/translation-pol-eng","datasets_with_task":"/datasets/task/translation-pol-eng"},{"name":"Translation kor-eng","url":"/task/translation-kor-eng","datasets_with_task":"/datasets/task/translation-kor-eng"},{"name":"Translation cat-fra","url":"/task/translation-cat-fra","datasets_with_task":"/datasets/task/translation-cat-fra"},{"name":"Translation cat-por","url":"/task/translation-cat-por","datasets_with_task":"/datasets/task/translation-cat-por"},{"name":"Translation cat-spa","url":"/task/translation-cat-spa","datasets_with_task":"/datasets/task/translation-cat-spa"},{"name":"Translation fra-por","url":"/task/translation-fra-por","datasets_with_task":"/datasets/task/translation-fra-por"},{"name":"Translation fra-spa","url":"/task/translation-fra-spa","datasets_with_task":"/datasets/task/translation-fra-spa"},{"name":"Translation glg-por","url":"/task/translation-glg-por","datasets_with_task":"/datasets/task/translation-glg-por"},{"name":"Translation glg-spa","url":"/task/translation-glg-spa","datasets_with_task":"/datasets/task/translation-glg-spa"},{"name":"Translation ita-por","url":"/task/translation-ita-por","datasets_with_task":"/datasets/task/translation-ita-por"},{"name":"Translation ita-spa","url":"/task/translation-ita-spa","datasets_with_task":"/datasets/task/translation-ita-spa"},{"name":"Translation oci-fra","url":"/task/translation-oci-fra","datasets_with_task":"/datasets/task/translation-oci-fra"},{"name":"Translation por-fra","url":"/task/translation-por-fra","datasets_with_task":"/datasets/task/translation-por-fra"},{"name":"Translation por-spa","url":"/task/translation-por-spa","datasets_with_task":"/datasets/task/translation-por-spa"},{"name":"Translation ron-fra","url":"/task/translation-ron-fra","datasets_with_task":"/datasets/task/translation-ron-fra"},{"name":"Translation ron-spa","url":"/task/translation-ron-spa","datasets_with_task":"/datasets/task/translation-ron-spa"},{"name":"Translation bul-fra","url":"/task/translation-bul-fra","datasets_with_task":"/datasets/task/translation-bul-fra"},{"name":"Translation bul-spa","url":"/task/translation-bul-spa","datasets_with_task":"/datasets/task/translation-bul-spa"},{"name":"Translation hrv-fra","url":"/task/translation-hrv-fra","datasets_with_task":"/datasets/task/translation-hrv-fra"},{"name":"Translation hrv-spa","url":"/task/translation-hrv-spa","datasets_with_task":"/datasets/task/translation-hrv-spa"},{"name":"Translation mkd-spa","url":"/task/translation-mkd-spa","datasets_with_task":"/datasets/task/translation-mkd-spa"},{"name":"Translation slv-fra","url":"/task/translation-slv-fra","datasets_with_task":"/datasets/task/translation-slv-fra"},{"name":"Translation hbs-fra","url":"/task/translation-hbs-fra","datasets_with_task":"/datasets/task/translation-hbs-fra"},{"name":"Translation hbs-spa","url":"/task/translation-hbs-spa","datasets_with_task":"/datasets/task/translation-hbs-spa"},{"name":"Translation dan-fra","url":"/task/translation-dan-fra","datasets_with_task":"/datasets/task/translation-dan-fra"},{"name":"Translation dan-spa","url":"/task/translation-dan-spa","datasets_with_task":"/datasets/task/translation-dan-spa"},{"name":"Translation isl-spa","url":"/task/translation-isl-spa","datasets_with_task":"/datasets/task/translation-isl-spa"},{"name":"Translation ara-fra","url":"/task/translation-ara-fra","datasets_with_task":"/datasets/task/translation-ara-fra"},{"name":"Translation ara-spa","url":"/task/translation-ara-spa","datasets_with_task":"/datasets/task/translation-ara-spa"},{"name":"Translation bul-deu","url":"/task/translation-bul-deu","datasets_with_task":"/datasets/task/translation-bul-deu"},{"name":"Translation hrv-deu","url":"/task/translation-hrv-deu","datasets_with_task":"/datasets/task/translation-hrv-deu"},{"name":"Translation slv-deu","url":"/task/translation-slv-deu","datasets_with_task":"/datasets/task/translation-slv-deu"},{"name":"Translation hbs-deu","url":"/task/translation-hbs-deu","datasets_with_task":"/datasets/task/translation-hbs-deu"},{"name":"Translation deu-spa","url":"/task/translation-deu-spa","datasets_with_task":"/datasets/task/translation-deu-spa"},{"name":"Translation heb-fra","url":"/task/translation-heb-fra","datasets_with_task":"/datasets/task/translation-heb-fra"},{"name":"Translation heb-por","url":"/task/translation-heb-por","datasets_with_task":"/datasets/task/translation-heb-por"},{"name":"Translation heb-spa","url":"/task/translation-heb-spa","datasets_with_task":"/datasets/task/translation-heb-spa"},{"name":"Translation fas-fra","url":"/task/translation-fas-fra","datasets_with_task":"/datasets/task/translation-fas-fra"},{"name":"Translation eus-spa","url":"/task/translation-eus-spa","datasets_with_task":"/datasets/task/translation-eus-spa"},{"name":"Translation deu-deu","url":"/task/translation-deu-deu","datasets_with_task":"/datasets/task/translation-deu-deu"},{"name":"Translation eng-eng","url":"/task/translation-eng-eng","datasets_with_task":"/datasets/task/translation-eng-eng"},{"name":"Translation afr-spa","url":"/task/translation-afr-spa","datasets_with_task":"/datasets/task/translation-afr-spa"},{"name":"Translation awa-eng","url":"/task/translation-awa-eng","datasets_with_task":"/datasets/task/translation-awa-eng"},{"name":"Translation ben-eng","url":"/task/translation-ben-eng","datasets_with_task":"/datasets/task/translation-ben-eng"},{"name":"Translation ceb-eng","url":"/task/translation-ceb-eng","datasets_with_task":"/datasets/task/translation-ceb-eng"},{"name":"Translation ces-deu","url":"/task/translation-ces-deu","datasets_with_task":"/datasets/task/translation-ces-deu"},{"name":"Translation ces-spa","url":"/task/translation-ces-spa","datasets_with_task":"/datasets/task/translation-ces-spa"},{"name":"Translation dan-deu","url":"/task/translation-dan-deu","datasets_with_task":"/datasets/task/translation-dan-deu"},{"name":"Translation deu-fra","url":"/task/translation-deu-fra","datasets_with_task":"/datasets/task/translation-deu-fra"},{"name":"Translation deu-por","url":"/task/translation-deu-por","datasets_with_task":"/datasets/task/translation-deu-por"},{"name":"Translation ell-deu","url":"/task/translation-ell-deu","datasets_with_task":"/datasets/task/translation-ell-deu"},{"name":"Translation ell-fra","url":"/task/translation-ell-fra","datasets_with_task":"/datasets/task/translation-ell-fra"},{"name":"Translation ell-por","url":"/task/translation-ell-por","datasets_with_task":"/datasets/task/translation-ell-por"},{"name":"Translation ell-spa","url":"/task/translation-ell-spa","datasets_with_task":"/datasets/task/translation-ell-spa"},{"name":"Translation epo-deu","url":"/task/translation-epo-deu","datasets_with_task":"/datasets/task/translation-epo-deu"},{"name":"Translation epo-eng","url":"/task/translation-epo-eng","datasets_with_task":"/datasets/task/translation-epo-eng"},{"name":"Translation epo-fra","url":"/task/translation-epo-fra","datasets_with_task":"/datasets/task/translation-epo-fra"},{"name":"Translation epo-por","url":"/task/translation-epo-por","datasets_with_task":"/datasets/task/translation-epo-por"},{"name":"Translation epo-spa","url":"/task/translation-epo-spa","datasets_with_task":"/datasets/task/translation-epo-spa"},{"name":"Translation est-deu","url":"/task/translation-est-deu","datasets_with_task":"/datasets/task/translation-est-deu"},{"name":"Translation eus-deu","url":"/task/translation-eus-deu","datasets_with_task":"/datasets/task/translation-eus-deu"},{"name":"Translation hin-eng","url":"/task/translation-hin-eng","datasets_with_task":"/datasets/task/translation-hin-eng"},{"name":"Translation hun-deu","url":"/task/translation-hun-deu","datasets_with_task":"/datasets/task/translation-hun-deu"},{"name":"Translation hun-fra","url":"/task/translation-hun-fra","datasets_with_task":"/datasets/task/translation-hun-fra"},{"name":"Translation hun-por","url":"/task/translation-hun-por","datasets_with_task":"/datasets/task/translation-hun-por"},{"name":"Translation hun-spa","url":"/task/translation-hun-spa","datasets_with_task":"/datasets/task/translation-hun-spa"},{"name":"Translation hye-eng","url":"/task/translation-hye-eng","datasets_with_task":"/datasets/task/translation-hye-eng"},{"name":"Translation ilo-eng","url":"/task/translation-ilo-eng","datasets_with_task":"/datasets/task/translation-ilo-eng"},{"name":"Translation ind-deu","url":"/task/translation-ind-deu","datasets_with_task":"/datasets/task/translation-ind-deu"},{"name":"Translation ind-eng","url":"/task/translation-ind-eng","datasets_with_task":"/datasets/task/translation-ind-eng"},{"name":"Translation ind-fra","url":"/task/translation-ind-fra","datasets_with_task":"/datasets/task/translation-ind-fra"},{"name":"Translation isl-deu","url":"/task/translation-isl-deu","datasets_with_task":"/datasets/task/translation-isl-deu"},{"name":"Translation ita-deu","url":"/task/translation-ita-deu","datasets_with_task":"/datasets/task/translation-ita-deu"},{"name":"Translation jpn-eng","url":"/task/translation-jpn-eng","datasets_with_task":"/datasets/task/translation-jpn-eng"},{"name":"Translation jpn-fra","url":"/task/translation-jpn-fra","datasets_with_task":"/datasets/task/translation-jpn-fra"},{"name":"Translation jpn-por","url":"/task/translation-jpn-por","datasets_with_task":"/datasets/task/translation-jpn-por"},{"name":"Translation jpn-spa","url":"/task/translation-jpn-spa","datasets_with_task":"/datasets/task/translation-jpn-spa"},{"name":"Translation kat-eng","url":"/task/translation-kat-eng","datasets_with_task":"/datasets/task/translation-kat-eng"},{"name":"Translation kaz-eng","url":"/task/translation-kaz-eng","datasets_with_task":"/datasets/task/translation-kaz-eng"},{"name":"Translation mal-eng","url":"/task/translation-mal-eng","datasets_with_task":"/datasets/task/translation-mal-eng"},{"name":"Translation mar-eng","url":"/task/translation-mar-eng","datasets_with_task":"/datasets/task/translation-mar-eng"},{"name":"Translation mlt-eng","url":"/task/translation-mlt-eng","datasets_with_task":"/datasets/task/translation-mlt-eng"},{"name":"Translation pes-eng","url":"/task/translation-pes-eng","datasets_with_task":"/datasets/task/translation-pes-eng"},{"name":"Translation pol-deu","url":"/task/translation-pol-deu","datasets_with_task":"/datasets/task/translation-pol-deu"},{"name":"Translation pol-fra","url":"/task/translation-pol-fra","datasets_with_task":"/datasets/task/translation-pol-fra"},{"name":"Translation pol-por","url":"/task/translation-pol-por","datasets_with_task":"/datasets/task/translation-pol-por"},{"name":"Translation pol-spa","url":"/task/translation-pol-spa","datasets_with_task":"/datasets/task/translation-pol-spa"},{"name":"Translation por-deu","url":"/task/translation-por-deu","datasets_with_task":"/datasets/task/translation-por-deu"},{"name":"Translation ron-deu","url":"/task/translation-ron-deu","datasets_with_task":"/datasets/task/translation-ron-deu"},{"name":"Translation ron-eng","url":"/task/translation-ron-eng","datasets_with_task":"/datasets/task/translation-ron-eng"},{"name":"Translation run-eng","url":"/task/translation-run-eng","datasets_with_task":"/datasets/task/translation-run-eng"},{"name":"Translation run-fra","url":"/task/translation-run-fra","datasets_with_task":"/datasets/task/translation-run-fra"},{"name":"Translation fas-deu","url":"/task/translation-fas-deu","datasets_with_task":"/datasets/task/translation-fas-deu"},{"name":"Translation msa-deu","url":"/task/translation-msa-deu","datasets_with_task":"/datasets/task/translation-msa-deu"},{"name":"Translation msa-eng","url":"/task/translation-msa-eng","datasets_with_task":"/datasets/task/translation-msa-eng"},{"name":"Translation ara-deu","url":"/task/translation-ara-deu","datasets_with_task":"/datasets/task/translation-ara-deu"},{"name":"Translation cmn_Hans-eng","url":"/task/translation-cmn-hans-eng","datasets_with_task":"/datasets/task/translation-cmn-hans-eng"},{"name":"Translation cmn_Hans-fra","url":"/task/translation-cmn-hans-fra","datasets_with_task":"/datasets/task/translation-cmn-hans-fra"},{"name":"Translation cmn_Hans-por","url":"/task/translation-cmn-hans-por","datasets_with_task":"/datasets/task/translation-cmn-hans-por"},{"name":"Translation cmn_Hans-spa","url":"/task/translation-cmn-hans-spa","datasets_with_task":"/datasets/task/translation-cmn-hans-spa"},{"name":"Translation cmn_Hant-eng","url":"/task/translation-cmn-hant-eng","datasets_with_task":"/datasets/task/translation-cmn-hant-eng"},{"name":"Translation cmn_Hant-fra","url":"/task/translation-cmn-hant-fra","datasets_with_task":"/datasets/task/translation-cmn-hant-fra"},{"name":"Translation cmn_Hant-por","url":"/task/translation-cmn-hant-por","datasets_with_task":"/datasets/task/translation-cmn-hant-por"},{"name":"Translation cmn_Hant-spa","url":"/task/translation-cmn-hant-spa","datasets_with_task":"/datasets/task/translation-cmn-hant-spa"},{"name":"Translation dsb-deu","url":"/task/translation-dsb-deu","datasets_with_task":"/datasets/task/translation-dsb-deu"},{"name":"Translation hsb-deu","url":"/task/translation-hsb-deu","datasets_with_task":"/datasets/task/translation-hsb-deu"},{"name":"Translation ido_Latn-eng","url":"/task/translation-ido-latn-eng","datasets_with_task":"/datasets/task/translation-ido-latn-eng"},{"name":"Translation kaz_Cyrl-eng","url":"/task/translation-kaz-cyrl-eng","datasets_with_task":"/datasets/task/translation-kaz-cyrl-eng"},{"name":"Translation lfn_Latn-deu","url":"/task/translation-lfn-latn-deu","datasets_with_task":"/datasets/task/translation-lfn-latn-deu"},{"name":"Translation lfn_Latn-eng","url":"/task/translation-lfn-latn-eng","datasets_with_task":"/datasets/task/translation-lfn-latn-eng"},{"name":"Translation lfn_Latn-por","url":"/task/translation-lfn-latn-por","datasets_with_task":"/datasets/task/translation-lfn-latn-por"},{"name":"Translation nor-deu","url":"/task/translation-nor-deu","datasets_with_task":"/datasets/task/translation-nor-deu"},{"name":"Translation por-por","url":"/task/translation-por-por","datasets_with_task":"/datasets/task/translation-por-por"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["tatoeba-test-v2021-08-07","tatoeba-test-v2021-03-30","tatoeba-test-v2021-02-22","tatoeba-test-v2020-07-28-v2021-08-07","tatoeba-test-v2020-07-28","Tatoeba-test.eng-deu","tatoeba-test","Tatoeba (EN-to-EL)","Tatoeba (EL-to-EN)","tatoeba v2021-08-07 yid-eng","tatoeba v2021-08-07 yid-deu","tatoeba v2021-08-07 swg-deu","tatoeba v2021-08-07 nld-nds","tatoeba v2021-08-07 nld-ltz","tatoeba v2021-08-07 nld-fry","tatoeba v2021-08-07 nld-eng","tatoeba v2021-08-07 nld-deu","tatoeba v2021-08-07 nld-afr","tatoeba v2021-08-07 nds-nld","tatoeba v2021-08-07 nds-eng","tatoeba v2021-08-07 nds-deu","tatoeba v2021-08-07 ltz-nld","tatoeba v2021-08-07 ltz-eng","tatoeba v2021-08-07 ltz-deu","tatoeba v2021-08-07 hrx-eng","tatoeba v2021-08-07 hrx-deu","tatoeba v2021-08-07 gsw-eng","tatoeba v2021-08-07 gos-nld","tatoeba v2021-08-07 gos-eng","tatoeba v2021-08-07 gos-deu","tatoeba v2021-08-07 fry-nld","tatoeba v2021-08-07 fry-eng","tatoeba v2021-08-07 frr-deu","tatoeba v2021-08-07 eng-yid","tatoeba v2021-08-07 eng-nld","tatoeba v2021-08-07 eng-nds","tatoeba v2021-08-07 eng-ltz","tatoeba v2021-08-07 eng-fry","tatoeba v2021-08-07 eng-deu","tatoeba v2021-08-07 eng-afr","tatoeba v2021-08-07 deu-yid","tatoeba v2021-08-07 deu-nld","tatoeba v2021-08-07 deu-nds","tatoeba v2021-08-07 deu-ltz","tatoeba v2021-08-07 deu-eng","tatoeba v2021-08-07 deu-afr","tatoeba v2021-03-30 ang-eng","tatoeba v2021-08-07 afr-nld","tatoeba v2021-08-07 afr-eng","tatoeba v2021-08-07 afr-deu","Tatoeba - Test","Tatoeba"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Helsinki-NLP/tatoeba","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tatoeba","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":38,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/machine-translation-on-tatoeba-el-to-en","task":"Machine Translation","dataset_variant":"Tatoeba (EL-to-EN)","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"PENELOPIE (Transformers-based Greek-to-English NMT)","paper":"/paper/penelopie-enabling-open-information","metrics":{"BLEU":"79.3"},"code_links":[{"title":"lighteternal/PENELOPIE","url":"https://github.com/lighteternal/PENELOPIE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/machine-translation-on-tatoeba-en-to-el","task":"Machine Translation","dataset_variant":"Tatoeba (EN-to-EL)","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"PENELOPIE Transformers-based NMT (EN2EL)","paper":"/paper/penelopie-enabling-open-information","metrics":{"BLEU":"76.9"},"code_links":[{"title":"lighteternal/PENELOPIE","url":"https://github.com/lighteternal/PENELOPIE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/penelopie-enabling-open-information","title":"PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation","date":"2021-03-28","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}