{"url":"/dataset/newsph-nli","name":"NewsPH-NLI","full_name":null,"description_markdown":"NewsPH-NLI is a sentence entailment benchmark dataset in the low-resource Filipino language. \r\n\r\nSource: [Investigating the True Performance of Transformers in Low-Resource Languages: A Case Study in Automatic Corpus Creation](/paper/investigating-the-true-performance-of)","description_withheld":null,"homepage":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/investigating-the-true-performance-of","title":"Exploiting News Article Structure for Automatic Corpus Generation of Entailment Datasets","first_author":"Jan Christian Blaise Cruz","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[{"name":"Filipino","url":"/datasets/language/filipino"}],"variants":["NewsPH-NLI"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jcblaise/newsph_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jcblaise/newsph","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/newsph","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/newsph_nli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","url":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","frameworks":["tf"]}],"num_papers_in_archive":2,"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."}