{"url":"/dataset/indosum","name":"IndoSum","full_name":null,"description_markdown":"The **IndoSum** dataset is a benchmark dataset for Indonesian text summarization. The dataset consists of news articles and manually constructed summaries.\n\nSource: [https://github.com/kata-ai/indosum](https://github.com/kata-ai/indosum)","description_withheld":null,"homepage":"https://github.com/kata-ai/indosum","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/indosum-a-new-benchmark-dataset-for","title":"IndoSum: A New Benchmark Dataset for Indonesian Text Summarization","first_author":"Kemal Kurniawan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"Indonesian","url":"/datasets/language/indonesian"}],"variants":["IndoSum"],"data_loaders":[{"repo":"https://github.com/kata-ai/indosum","url":"https://github.com/kata-ai/indosum","frameworks":["tf"]}],"num_papers_in_archive":9,"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."}