{"url":"/dataset/vinli","name":"ViNLI","full_name":"Vietnamese Natural Language Inference Dataset","description_markdown":"A large-scale and high-quality corpus is necessary for studies on NLI for Vietnamese, which can be considered a low-resource language. In this paper, we introduce ViNLI (Vietnamese Natural Language Inference), an open-domain and high-quality corpus for evaluating Vietnamese NLI models, which is created and evaluated with a strict process of quality control. ViNLI comprises over 30,000 human-annotated premise-hypothesis sentence pairs extracted from more than 800 online news articles on 13 distinct topics.","description_withheld":null,"homepage":"https://nlp.uit.edu.vn/","introduced_date":"2022-10-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/vinli-a-vietnamese-corpus-for-studies-on-open","title":"ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference","first_author":"Tin Van Huynh","url":null},"license":null,"modalities":[],"tasks":[{"name":"Vietnamese Natural Language Inference","url":"/task/vietnamese-natural-language-inference","datasets_with_task":"/datasets/task/vietnamese-natural-language-inference"}],"languages":[{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["ViNLI"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/vietnamese-natural-language-inference-on","task":"Vietnamese Natural Language Inference","dataset_variant":"ViNLI","rows":2,"metrics":["3-class test accuracy","4-class test accuracy"],"first_row_in_archive_order":{"model":"XLM-R-large","paper":"/paper/vinli-a-vietnamese-corpus-for-studies-on-open","metrics":{"3-class test accuracy":"81.36","4-class test accuracy":"85.99"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vlue-a-new-benchmark-and-multi-task-knowledge","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","date":"2024-03-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vinli-a-vietnamese-corpus-for-studies-on-open","title":"ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference","date":"2022-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"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."}