{"url":"/dataset/pre-trained-transliterated-embeddings-for","name":"Pre-trained Transliterated Embeddings for Indian Languages","full_name":null,"description_markdown":"We release various types of word embeddings for multiple Indian languages. Please note that for a majority of our work, we had transliterated the corpora to the Devanagiri script and the script is changed. Word Embedding models using FastText, ElMo, and cross-lingual models based on an orthogonal alignment of monolingual models for all pairs of these languages.","description_withheld":null,"homepage":"https://www.cfilt.iitb.ac.in/~diptesh/embeddings/","introduced_date":"2021-12-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-passage-to-india-pre-trained-word-1","title":"\"A Passage to India\": Pre-trained Word Embeddings for Indian Languages","first_author":"Kumar Saurav","url":null},"license":{"name":"CC-BY-NC-4.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"}],"languages":[{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["Pre-trained Transliterated Embeddings for Indian Languages"],"data_loaders":[],"num_papers_in_archive":1,"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."}