{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"dsfsi-lid","owner":"dsfsi","isFork":false,"description":"Language Identification For South African languages","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":1,"starsCount":0,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-31T08:30:45.131Z"}},{"type":"Public","name":"deadlines","owner":"dsfsi","isFork":true,"description":"⏰ AI/ML/DS conference/workshop/event deadlines on the African continent","allTopics":[],"primaryLanguage":{"name":"HTML","color":"#e34c26"},"pullRequestCount":0,"issueCount":0,"starsCount":17,"forksCount":930,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-11T18:58:53.904Z"}},{"type":"Public","name":"gov-za-multilingual","owner":"dsfsi","isFork":false,"description":"The data set contains cabinet statements from the South African government. Data was scraped from the governments website: <a href=\"https://www.gov.za/cabinet-statements\" rel=\"nofollow\">https://www.gov.za/cabinet-statements</a>","allTopics":["language","machine-learning","corpus","dataset","south-africa","nlproc","africanlp","africannlp","african-language-data-liberation-front","dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-10T14:27:33.039Z"}},{"type":"Public","name":"dsfsi-datasets","owner":"dsfsi","isFork":false,"description":"Datasets made available for different small projects","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-06T08:55:57.514Z"}},{"type":"Public","name":"simcse","owner":"dsfsi","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-29T07:41:49.392Z"}},{"type":"Public template","name":"academic-project-page-template","owner":"dsfsi","isFork":true,"description":"A project page template for academic papers. Demo at <a href=\"https://eliahuhorwitz.github.io/Academic-project-page-template/\" rel=\"nofollow\">https://eliahuhorwitz.github.io/Academic-project-page-template/</a>","allTopics":[],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":179,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-02T09:02:59.485Z"}},{"type":"Public","name":".github","owner":"dsfsi","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-21T07:47:50.774Z"}},{"type":"Public","name":"datacommonsorg-data","owner":"dsfsi","isFork":true,"description":"","allTopics":[],"primaryLanguage":{"name":"HTML","color":"#e34c26"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":103,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-16T23:16:05.590Z"}},{"type":"Public","name":"textaugment","owner":"dsfsi","isFork":false,"description":"TextAugment: Text Augmentation Library","allTopics":["wordnet","hacktoberfest","synonym","augmentation","mixup","augmentation-methods","low-resouce-language","nlp-augmentation","nlp","natural-language-processing","word2vec"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":5,"issueCount":5,"starsCount":381,"forksCount":60,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-20T11:57:52.765Z"}},{"type":"Public","name":"bibtextomd","owner":"dsfsi","isFork":true,"description":"Convert BibTeX entries to formatted Markdown","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":1,"starsCount":0,"forksCount":12,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-09T05:46:19.930Z"}},{"type":"Public","name":"vukuzenzele-nlp","owner":"dsfsi","isFork":true,"description":"The dataset contains editions from the South African government magazine Vuk'uzenzele. Data was scraped from PDFs that have been placed in the data/raw folder. The PDFS were obtained from the Vuk'uzenzele website.","allTopics":["language","dataset","african-languages","south-africa","nlproc","africanlp","africannlp","aldlf","african-language-data-liberation-front","dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":3,"starsCount":6,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-06T10:17:29.207Z"}},{"type":"Public","name":"covid19za","owner":"dsfsi","isFork":false,"description":"Coronavirus COVID-19 (2019-nCoV) Data Repository and Dashboard for South Africa","allTopics":["data-science","dashboard","doi","health","dataset","south-africa","doh","nicd","coronavirus","covid-19","covid19","covid-data","covid19-data","dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":5,"issueCount":37,"starsCount":255,"forksCount":200,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-06T09:00:30.673Z"}},{"type":"Public","name":"PuoBERTa","owner":"dsfsi","isFork":false,"description":"A Roberta-based language model specially designed for Setswana, using the new PuoData dataset.","allTopics":["african-languages","nlproc","tsn","tn","setswana","africannlp","dsfsi-datasets"],"primaryLanguage":{"name":"Makefile","color":"#427819"},"pullRequestCount":0,"issueCount":0,"starsCount":4,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-04T19:04:31.475Z"}},{"type":"Public","name":"cos802","owner":"dsfsi","isFork":false,"description":"Defense against the dark text arts","allTopics":[],"primaryLanguage":{"name":"SCSS","color":"#c6538c"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-08T13:55:55.180Z"}},{"type":"Public","name":"gov-za-sona-multilingual","owner":"dsfsi","isFork":false,"description":"","allTopics":["dsfsi-datasets"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":1,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-06T09:55:06.309Z"}},{"type":"Public","name":"edu-assessment-llm-prompt","owner":"dsfsi","isFork":false,"description":"Educational Assesement using LLMs","allTopics":["south-africa","large-language-models","llm","dsfsi-datasets","educational-assessment"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-06T07:49:50.213Z"}},{"type":"Public","name":"datacommonsorg-schema","owner":"dsfsi","isFork":true,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":23,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-31T14:06:47.102Z"}},{"type":"Public","name":"za-fake-news-2020","owner":"dsfsi","isFork":false,"description":"Dataset of South African Disinformation [Fake News] Website Data collected in 2020","allTopics":["south-africa","misinformation","disinformation","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":3,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:25:32.951Z"}},{"type":"Public","name":"healthfacilitymap","owner":"dsfsi","isFork":false,"description":"South African Health Facility map. Created to aid in covid19za responses","allTopics":["map","south-africa","covid-19","health-facility","covid19za","dsfsi-datasets"],"primaryLanguage":{"name":"JavaScript","color":"#f1e05a"},"pullRequestCount":0,"issueCount":1,"starsCount":0,"forksCount":1,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:25:23.761Z"}},{"type":"Public","name":"dlindaba-2019-uber","owner":"dsfsi","isFork":false,"description":"UBER Rider Rating Data from the DLIndaba 2019","allTopics":["dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:25:11.699Z"}},{"type":"Public","name":"izindaba-zesizulu","owner":"dsfsi","isFork":false,"description":"Categorised isiZulu News. Source data is the isiZulu news from the SABC social media posts. ","allTopics":["isizulu","africanlp","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:24:53.968Z"}},{"type":"Public","name":"StatsSA-Language","owner":"dsfsi","isFork":false,"description":" StatsSA statistical language glossary in machine-readable format","allTopics":["language","dataset","south-africa","statiscs","statssa-language","dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":2,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:24:40.070Z"}},{"type":"Public","name":"za-terminology","owner":"dsfsi","isFork":false,"description":"DSFSI South African Terminlogy Lists and Lexicon Project","allTopics":["machine-learning","natural-language-processing","terminology","terminologies","south-africa","nlproc","human-language-technologies","dsfsi-datasets"],"primaryLanguage":{"name":"Makefile","color":"#427819"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:24:30.719Z"}},{"type":"Public","name":"embedding-eval-data","owner":"dsfsi","isFork":false,"description":"Embedding Evaluation Data for South African Languages","allTopics":["nlp","machine-learning","africa","south-africa","nlproc","low-resource-languages","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:24:15.292Z"}},{"type":"Public","name":"za-bank-risk","owner":"dsfsi","isFork":false,"description":"This repository is an initial pipeline for reading, processing, labelling and classifying unstructured annual reports of South African (SA) banks with the aim of identifying financial risk. It leveraged work by the Corporate Financial Information Environment-Final Report Structure Extractor (CFIE–FRSE) of El-Haj et al. which created a corpus of …","allTopics":["nlp","finance","machine-learning","natural-language-processing","dataset","south-africa","african","nlproc","bank-risk","dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":"Creative Commons Attribution Share Alike 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:24:06.234Z"}},{"type":"Public","name":"za-isizulu-siswati-news-2022","owner":"dsfsi","isFork":false,"description":"IsiZulu News (articles and headlines) and Siswati News (headlines) Corpora - za-isizulu-siswati-news-2022","allTopics":["natural-language-processing","corpora","south-africa","low-resource-languages","news-categorizer","african-nlp","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Creative Commons Attribution Share Alike 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:20:35.177Z"}},{"type":"Public","name":"Higher_Education_EDA","owner":"dsfsi","isFork":false,"description":"This is an EDA Git for education researchers and practitioners","allTopics":["dsfsi-datasets"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":3,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:20:27.857Z"}},{"type":"Public","name":"sa-parliament","owner":"dsfsi","isFork":false,"description":"South African Member Of Parliament Data","allTopics":["parliament-data","sa-parliament","dsfsi-datasets"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":5,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:20:03.477Z"}},{"type":"Public","name":"PuoData","owner":"dsfsi","isFork":false,"description":"Curated corpora for Setswana. Used to train PuoBERTa.","allTopics":["natural-language-processing","corpora","african-languages","south-africa","tsn","tn","setswana","african-nlp","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":0,"license":"Creative Commons Attribution Share Alike 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:19:26.764Z"}},{"type":"Public","name":"project-state-capture","owner":"dsfsi","isFork":false,"description":"Zondo Commission or State Capture Commission Transcripts","allTopics":["nlp","natural-language-processing","south-africa","dsfsi-datasets"],"primaryLanguage":null,"pullRequestCount":0,"issueCount":3,"starsCount":2,"forksCount":0,"license":"Creative Commons Attribution Share Alike 4.0 International","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-26T07:19:14.135Z"}}],"repositoryCount":45,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}