{"url":"/dataset/balitanlp","name":"BalitaNLP","full_name":null,"description_markdown":"A Filipino multi-modal language dataset for text+visual tasks. Consists of 351,755 Filipino news articles gathered from Filipino news outlets.\r\n\r\nEach entry contains:\r\n\r\n* body - Article text\r\n* title - Article title\r\n* website - Name of the news outlet\r\n* category - News category given by the news outlet\r\n* date - Date published\r\n* author - Article author\r\n* url - URL of the article\r\n* img_url - URL of the article image\r\n* img_path - Filename of the image in the dataset","description_withheld":null,"homepage":"https://github.com/KenrickLance/BalitaNLP-Dataset","introduced_date":"2023-03-09","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"},{"name":"News Classification","url":"/task/news-classification","datasets_with_task":"/datasets/task/news-classification"},{"name":"News Generation","url":"/task/news-generation","datasets_with_task":"/datasets/task/news-generation"},{"name":"Conditional Text Generation","url":"/task/conditional-text-generation","datasets_with_task":"/datasets/task/conditional-text-generation"}],"languages":[{"name":"Filipino","url":"/datasets/language/filipino"}],"variants":["BalitaNLP"],"data_loaders":[],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}