{"url":"/dataset/indicnlp-corpus","name":"IndicNLP Corpus","full_name":null,"description_markdown":"The IndicNLP corpus is a large-scale, general-domain corpus containing 2.7 billion words for 10 Indian languages from two language families.\n\nSource: [https://arxiv.org/abs/2005.00085](https://arxiv.org/abs/2005.00085)","description_withheld":null,"homepage":"https://github.com/ai4bharat-indicnlp/indicnlp_corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ai4bharat-indicnlp-corpus-monolingual-corpora","title":"AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages","first_author":"Anoop Kunchukuttan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"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":"Bengali","url":"/datasets/language/bengali"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Kannada","url":"/datasets/language/kannada"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Oriya (macrolanguage)","url":"/datasets/language/oriya-macrolanguage"},{"name":"Punjabi","url":"/datasets/language/punjabi"}],"variants":["IndicNLP Corpus"],"data_loaders":[{"repo":"https://github.com/ai4bharat-indicnlp/indicnlp_corpus","url":"https://github.com/ai4bharat-indicnlp/indicnlp_corpus","frameworks":[]}],"num_papers_in_archive":3,"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."}