{"url":"/dataset/nergrit-corpus","name":"NERGRIT Corpus","full_name":null,"description_markdown":"NERGRIT involves machine learning based NLP Tools and a corpus used for Indonesian Named Entity Recognition, Statement Extraction, and Sentiment Analysis. \r\n\r\nSource: [NERGRIT Corpus](https://github.com/grit-id/nergrit-corpus)","description_withheld":null,"homepage":"https://github.com/grit-id/nergrit-corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Token Classification","url":"/task/token-classification","datasets_with_task":"/datasets/task/token-classification"}],"languages":[{"name":"Indonesian","url":"/datasets/language/indonesian"}],"variants":["NERGRIT Corpus","id_nergrit_corpus","grit-id/id_nergrit_corpus ner"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/grit-id/id_nergrit_corpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/id_nergrit_corpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/grit-id/nergrit-corpus","url":"https://github.com/grit-id/nergrit-corpus","frameworks":[]}],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/token-classification-on-grit-id-id-nergrit","task":"Token Classification","dataset_variant":"grit-id/id_nergrit_corpus ner","rows":0,"metrics":["Accuracy","F1","Precision","Recall"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"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."}