SADiLaR Language Resource Repository
Not a member yet
536 research outputs found
Sort by
Speech transcription platform speech services
No full textThis is the Language Technology Services component implemented for the Speech Transcription Platform project by the Multilingual Speech Technologies group at North-West University. The project was sponsored by the Department of Arts and Culture of South Africa.
The speech services module is broken up into two parts:
1. Speech server: Manages speech jobs.
2. Speech scheduler: Monitors a speech jobs database and manages requested or running speech jobs.
This repository contains software developed by third parties under their respective licences. For specific licence conditions please refer to the documentation contained in the relevant sub-directory or source code file.
Files and documentation are available at https://github.com/NWU-MuST/STP-service
Multilingual Arts & Culture Intermediate Phase Terminology List
No full text550 English source terms with their equivalents in the ten other official South African languages. The list was compiled in collaboration with subject field specialists. Terms were excerpted from arts and culture learner books, teacher’s guides and manuals, arts and culture journals and magazines, etc. Please contact the National Language Service for usage conditions
Multilingual Life Orientation Intermediate Phase Terminology List
No full text1628 English source terms with their equivalents in the ten other official South African languages. The terms were excerpted from life orientation learner's books, teacher guides and manuals. The list compiled in collaboration with subject field specialists. The purpose of the project was to produce a valuable source in the teaching and learning of Life Orientation. Please contact the National Language Service for usage conditions
Speech transcription platform user interface
No full textThis is the user interface component of the Speech Transcription Platform developed by the Multilingual Speech Technologies group at North-West University and the project was sponsored by the Department of Arts and Culture of South Africa.
There are two basic software dependencies for this component: 1) Apache2 Web server and 2) PHP (including Apache2 plugins)
Note: The repository contains software developed by third parties under their respective licences. For specific licence conditions please refer to the documentation contained in the relevant sub-directory or source code file.
Files and documentation are available at https://github.com/NWU-MuST/STP-U
African Wordnet: isiXhosa 1.0
No full textDeveloped using the expand model with Princeton WordNet 2.0 as basis. Each wordnet contains synsets with at least the following fields:\nWord form (lemma; synonym)\nID (linking to the Princeton Wordnet 2.0)\nPart of speech\nDomain\nSUMO/MILO classification\n\nAdditional data may include the following fields:\nUsage example(s)\nDefinition\nHypernym\nHyponym\nStamp\nNotes\nNon-lexicalisation\n\nPlease see https://africanwordnet.wordpress.com/ for all details on the projec
Multilingual HIV/AIDS Terminology List
No full text586 English source terms with their equivalents in the ten other official South African languages. The list was compiled in collaboration with subject field specialists, including the Department of Health, and verified by the National Language Bodies of PanSALB. The purpose of the project was to promote communication between the general public and health professionals and to inform and educate the public about HIV associated diseases and symptoms in a typical South African context. Please contact the National Language Service for usage conditions
Multilingual Parliamentary / Political Terminology List
No full text502 English source terms with their equivalents in the ten other official South African languages. The project built on a 2003 initiative of the national Parliament and the provincial legislatures of the Western and Eastern Cape. Terms were extracted from Hansard reports, parliamentary proceedings and papers, and legislation. Please contact the National Language Service for usage conditions
Multilingual Information Communication Technology Terminology List
No full text132 English source terms with their equivalents in the ten other official South African languages. Originally initiated by the Department of Communications, the list was compiled in collaboration with subject field specialists from the SABC, South African Postal Services and Telkom. The project was aimed at addressing the situation where many ordinary South Africans are not able to access technologies due to a lack of understanding of the concepts in their own languages. Please contact the National Language Service for usage conditions
African Wordnet: Setswana 1.0
No full textDeveloped using the expand model with Princeton WordNet 2.0 as basis.Each wordnet contains synsets with at least the following fields:\nWord form (lemma; synonym)\nID (linking to the Princeton Wordnet 2.0)\nPart of speech\nDomain\nSUMO/MILO classification\n\nAdditional data may include the following fields:\nUsage example(s)\nDefinition\nHypernym\nHyponym\nStamp\nNotes\nNon-lexicalisation\n\nPlease see https://africanwordnet.wordpress.com/ for all details on the projec
Autshumato Machine Translation Evaluation Set
No full textComparable evaluation data for use in automatic machine translation evaluations. The evaluation set consists of 500 sentences translated separately by four different professional human translators for each of the 11 official South African languages. This creates a set with four reference translations for each of the 11 languages where each of the texts can be used as an input text as well. This ensures that the evaluation set can be used to evaluate machine translation between any two of the 11 languages