f | { | f | { |
n | "access_rights": "Creative Commons license, Attribution - Non | n | "access_rights": "", |
| Commercial - No Derivatives (CC BY NC ND 4.0 International)", | | "author": "Marco Gaido", |
| "author": "Mattia Antonino Di Gangi", | | |
| "author_email": "", | | "author_email": "", |
n | "citation": [], | n | "citation": [ |
| | | "https://doi.org/10.48550/arXiv.2102.01578", |
| | | "https://doi.org/10.48550/arXiv.2012.04964", |
| | | "https://doi.org/10.48550/arXiv.2109.07439", |
| | | "https://doi.org/10.48550/arXiv.2109.07368", |
| | | "https://doi.org/10.48550/arXiv.2012.04955" |
| | | ], |
| "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", |
n | "defined_in": "https://doi.org/10.18653/v1/N19-1202", | n | "defined_in": "https://doi.org/10.48550/arXiv.2104.11710", |
| "doi": "10.57702/nhiwpvh5", | | "doi": "10.57702/nhiwpvh5", |
| "doi_date_published": "2024-11-25", | | "doi_date_published": "2024-11-25", |
| "doi_publisher": "TIB", | | "doi_publisher": "TIB", |
| "doi_status": true, | | "doi_status": true, |
| "domain": "https://service.tib.eu/ldmservice", | | "domain": "https://service.tib.eu/ldmservice", |
| "extra_authors": [ | | "extra_authors": [ |
| { | | { |
n | "extra_author": "Roldano Cattoni", | n | "extra_author": "Mauro Cettolo", |
| "orcid": "" | | |
| }, | | |
| { | | |
| "extra_author": "Luisa Bentivogli", | | |
| "orcid": "" | | "orcid": "" |
| }, | | }, |
| { | | { |
| "extra_author": "Matteo Negri", | | "extra_author": "Matteo Negri", |
| "orcid": "" | | "orcid": "" |
| }, | | }, |
| { | | { |
| "extra_author": "Marco Turchi", | | "extra_author": "Marco Turchi", |
| "orcid": "" | | "orcid": "" |
| } | | } |
| ], | | ], |
n | "groups": [], | n | "groups": [ |
| | | { |
| | | "description": "", |
| | | "display_name": "Multilingual Speech Translation", |
| | | "id": "542c1ea1-7574-41e7-b7f6-2a83cb48454f", |
| | | "image_display_url": "", |
| | | "name": "multilingual-speech-translation", |
| | | "title": "Multilingual Speech Translation" |
| | | }, |
| | | { |
| | | "description": "", |
| | | "display_name": "Multilingualism", |
| | | "id": "bb2b523b-0228-4568-a5d7-f40cb8bdd4d2", |
| | | "image_display_url": "", |
| | | "name": "multilingualism", |
| | | "title": "Multilingualism" |
| | | }, |
| | | { |
| | | "description": "", |
| | | "display_name": "Speech Translation", |
| | | "id": "4ca6c748-9884-4f4a-87b2-d8cb7e2db7e8", |
| | | "image_display_url": "", |
| | | "name": "speech-translation", |
| | | "title": "Speech Translation" |
| | | } |
| | | ], |
| "id": "73d69fef-0e36-4d6b-905c-da1d2d0a6f89", | | "id": "73d69fef-0e36-4d6b-905c-da1d2d0a6f89", |
| "isopen": false, | | "isopen": false, |
n | "landing_page": "mustc.fbk.eu", | n | "landing_page": "https://ict.fbk.eu/", |
| "license_title": null, | | "license_title": null, |
| "link_orkg": "", | | "link_orkg": "", |
| "metadata_created": "2024-11-25T15:01:11.618160", | | "metadata_created": "2024-11-25T15:01:11.618160", |
n | "metadata_modified": "2024-11-25T15:01:11.939040", | n | "metadata_modified": "2024-12-02T22:25:41.225752", |
| "name": "must-c", | | "name": "must-c", |
n | "notes": "MuST-C is a multilingual speech translation corpus | n | "notes": "MuST-C is a multilingual speech translation dataset, which |
| comprising at least 385 hours of audio recordings from English TED | | contains at least 385 hours of audio recordings from TED Talks, with |
| Talks, aligned at the sentence level with their manual transcriptions | | their manual transcriptions and translations at the sentence level.", |
| and translations.", | | |
| "num_resources": 1, | | "num_resources": 0, |
| "num_tags": 0, | | "num_tags": 11, |
| "organization": { | | "organization": { |
| "approval_status": "approved", | | "approval_status": "approved", |
| "created": "2024-11-25T12:11:38.292601", | | "created": "2024-11-25T12:11:38.292601", |
| "description": "", | | "description": "", |
| "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", | | "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", |
| "image_url": "", | | "image_url": "", |
| "is_organization": true, | | "is_organization": true, |
| "name": "no-organization", | | "name": "no-organization", |
| "state": "active", | | "state": "active", |
| "title": "No Organization", | | "title": "No Organization", |
| "type": "organization" | | "type": "organization" |
| }, | | }, |
| "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", | | "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", |
| "private": false, | | "private": false, |
| "relationships_as_object": [], | | "relationships_as_object": [], |
| "relationships_as_subject": [], | | "relationships_as_subject": [], |
n | "resources": [ | n | "resources": [], |
| | | "services_used_list": "", |
| | | "state": "active", |
| | | "tags": [ |
| { | | { |
n | "cache_last_updated": null, | n | "display_name": "Corpus", |
| "cache_url": null, | | "id": "5e434f4b-89f6-489e-9e6e-d2ff6003d493", |
| "created": "2024-11-25T15:30:26", | | "name": "Corpus", |
| "data": [ | | |
| "dcterms:title", | | |
| "dcterms:accessRights", | | |
| "dcterms:creator", | | |
| "dcterms:description", | | |
| "dcterms:issued", | | |
| "dcterms:language", | | |
| "dcterms:identifier", | | |
| "dcat:theme", | | |
| "dcterms:type", | | |
| "dcat:keyword", | | |
| "dcat:landingPage", | | |
| "dcterms:hasVersion", | | |
| "dcterms:format", | | |
| "mls:task", | | |
| "datacite:isDescribedBy" | | |
| ], | | |
| "description": "The json representation of the dataset with its | | |
| distributions based on DCAT.", | | |
| "format": "JSON", | | |
| "hash": "", | | |
| "id": "4faf8016-7e48-4735-8bbc-c711db92dc51", | | |
| "last_modified": "2024-11-25T15:01:11.932173", | | |
| "metadata_modified": "2024-11-25T15:01:11.941762", | | |
| "mimetype": "application/json", | | |
| "mimetype_inner": null, | | |
| "name": "Original Metadata", | | |
| "package_id": "73d69fef-0e36-4d6b-905c-da1d2d0a6f89", | | |
| "position": 0, | | |
| "resource_type": null, | | |
| "size": 1042, | | |
| "state": "active", | | "state": "active", |
n | "url": | n | "vocabulary_id": null |
| resource/4faf8016-7e48-4735-8bbc-c711db92dc51/download/metadata.json", | | }, |
| "url_type": "upload" | | { |
| | | "display_name": "End-to-End", |
| | | "id": "d0b8290d-358b-4d71-977f-c5fd5b1e28fe", |
| | | "name": "End-to-End", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "Machine Translation", |
| | | "id": "55f5baba-6c20-44c5-b149-da1768badaf4", |
| | | "name": "Machine Translation", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "Multilingual", |
| | | "id": "6de060ee-b4b7-4b76-b978-29ec374b6594", |
| | | "name": "Multilingual", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "Speech Recognition", |
| | | "id": "eebd420b-8b14-4294-ade4-4917392439bf", |
| | | "name": "Speech Recognition", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "Speech Translation", |
| | | "id": "4a77e43c-63c7-4c5b-ae95-9e770134e744", |
| | | "name": "Speech Translation", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "TED Talks", |
| | | "id": "1c17b115-d6fc-4548-8bbc-d6469011dd6c", |
| | | "name": "TED Talks", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "TED talks", |
| | | "id": "33ed940d-d7a5-4bcb-8f94-94f562f5bd08", |
| | | "name": "TED talks", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "Text Data", |
| | | "id": "a72366d9-3035-43be-8190-608b1c5c787b", |
| | | "name": "Text Data", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "multilingualism", |
| | | "id": "da99b005-32c0-4a98-89cd-755f694ee9f6", |
| | | "name": "multilingualism", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| | | }, |
| | | { |
| | | "display_name": "speech translation", |
| | | "id": "2583d66f-39d7-4a6a-b8c5-f62d83f5f4e6", |
| | | "name": "speech translation", |
| | | "state": "active", |
| | | "vocabulary_id": null |
| } | | } |
| ], | | ], |
t | "services_used_list": "", | t | |
| "state": "active", | | |
| "tags": [], | | |
| "title": "MuST-C", | | "title": "MuST-C", |
| "type": "dataset", | | "type": "dataset", |
| "version": "" | | "version": "" |
| } | | } |