{"url":"/dataset/indonlg","name":"IndoNLG","full_name":null,"description_markdown":"IndoNLG is a benchmark to measure natural language generation (NLG) progress in three low-resource—yet widely spoken—languages of Indonesia: Indonesian, Javanese, and Sundanese. Altogether, these languages are spoken by more than 100 million native speakers, and hence constitute an important use case of NLG systems today. Concretely, IndoNLG covers six tasks: summarization, question answering, chit-chat, and three different pairs of machine translation (MT) tasks.","description_withheld":null,"homepage":"https://github.com/indobenchmark/indonlg","introduced_date":"2021-04-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/indonlg-benchmark-and-resources-for","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","first_author":"Samuel Cahyawijaya","url":null},"license":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Javanese","url":"/datasets/language/javanese"},{"name":"Sundanese","url":"/datasets/language/sundanese"}],"variants":["IndoNLG"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/GEM/indonlg","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":4,"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."}