{"id":883,"slug":"hltcoe--megawika","name":"megawika","author":"hltcoe","description":"MegaWika is a multi- and crosslingual text dataset containing 30 million\nWikipedia passages with their scraped and cleaned web citations. The\npassages span 50 Wikipedias in 50 languages, and the articles in which\nthe passages were originally embedded are included for convenience. Where\na Wikipedia passage is in a non-English language, an automated English\ntranslation is provided. Furthermore, nearly 130 million English\nquestion/answer pairs were extracted from the passages, and FrameNet events\noccurring in the passages are detected using the LOME FrameNet parser.","tags":"[\"Task_categories:summarization\",\"Task_categories:question-Answering\",\"Task_categories:text-Generation\",\"Language:af\",\"Language:ar\",\"Language:az\"]","license":null,"framework":null,"parameters":null,"downloads":133502,"likes":42,"verified":0,"created_at":"2026-09-08 10:23:27","updated_at":"2026-09-19 20:23:28","source_url":"https://huggingface.co/datasets/hltcoe/megawika","source_platform":"huggingface","hf_repo_id":"hltcoe/megawika","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":882,"model_id":883,"version":"v1.0.0","manifest_hash":"f8089a960e8455a840e1880f8147abdb03e7b7f13d462e6a9dd44135939ce327","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/hltcoe--megawika/v1.0.0.json","created_at":"2026-09-08 10:23:27"}],"files":[],"signatures":[{"id":1455,"version_id":882,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"7a8aa14e532663afc9e984b27384e7e186b3c78c0596e697f6dba76e5b75ca56","attestation_type":"registry","signed_at":"2026-09-08 10:23:27"}],"hndl":null}